Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:592a071277d7dbdd1c617566970c30ac2b551da1eaed76a15105874f1e84bab3
+oid sha256:52fae1249f12c00bad6d1cc4bfe18450bcfadd3fd7fe8ea394344ae711aad659
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a2b344395ce11576043e7c052bff0f1a1386778425f13dc8b17af596eacca7
+oid sha256:cb3af33a8c8b6c515aedd7cc0981c548148926854dcea8fc6b1d3b2df468452b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8768f11faafaf609b97f17843f0a66920ad1805e1eb20b8f94f0e22cf4f2db0
+oid sha256:3e2c2d45296a0fdaabba51b451e88c20955b4d6bf201085e8ae1d966230a5e54
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69edc65d5c26ddd406d174c709b4d1e3761f6a7fa4eee62d8ff230971646730
+oid sha256:52181f636e3c0609d10af30f0cad923f7ad72b2f6f566245198ebd89a9d6dc34
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4212ede83693fa8abd816f8b7feeb98146abb6d0463678d0a48ca5091aa7fe20
+oid sha256:a60b487c0ca8aa99376f0281424a417f4cf77e1ce39b250b7332a9c6b81942ee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913bba2e6c108d6f0557fdef61492c1323b5d30ec958d056ef8d7e116de580b2
+oid sha256:88021f0617d63346a5eeddc3e7a91b6ad2d7d49918ed3bfabf9b41d20fb3a3af
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4111673831939697,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.024466328215793014,
+  "best_metric": 2.397162914276123,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04893265643158603,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 24.595,
       "eval_steps_per_second": 6.395,
       "step": 25
+    },
+    {
+      "epoch": 0.025444981344424737,
+      "grad_norm": 0.1908201426267624,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.186,
+      "step": 26
+    },
+    {
+      "epoch": 0.026423634473056457,
+      "grad_norm": 0.23226866126060486,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.2756,
+      "step": 27
+    },
+    {
+      "epoch": 0.027402287601688176,
+      "grad_norm": 0.2683747410774231,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.3146,
+      "step": 28
+    },
+    {
+      "epoch": 0.0283809407303199,
+      "grad_norm": 0.295396089553833,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.3337,
+      "step": 29
+    },
+    {
+      "epoch": 0.029359593858951618,
+      "grad_norm": 0.3223787546157837,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.2585,
+      "step": 30
+    },
+    {
+      "epoch": 0.030338246987583337,
+      "grad_norm": 0.3190826177597046,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.2912,
+      "step": 31
+    },
+    {
+      "epoch": 0.03131690011621506,
+      "grad_norm": 0.33541804552078247,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.2797,
+      "step": 32
+    },
+    {
+      "epoch": 0.03229555324484678,
+      "grad_norm": 0.31905463337898254,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.3301,
+      "step": 33
+    },
+    {
+      "epoch": 0.0332742063734785,
+      "grad_norm": 0.3051736354827881,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.3091,
+      "step": 34
+    },
+    {
+      "epoch": 0.03425285950211022,
+      "grad_norm": 0.3700856566429138,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.3587,
+      "step": 35
+    },
+    {
+      "epoch": 0.035231512630741944,
+      "grad_norm": 0.3710134029388428,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.2941,
+      "step": 36
+    },
+    {
+      "epoch": 0.036210165759373664,
+      "grad_norm": 0.42295482754707336,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.3233,
+      "step": 37
+    },
+    {
+      "epoch": 0.03718881888800538,
+      "grad_norm": 0.18501313030719757,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.1554,
+      "step": 38
+    },
+    {
+      "epoch": 0.0381674720166371,
+      "grad_norm": 0.1772017776966095,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.2334,
+      "step": 39
+    },
+    {
+      "epoch": 0.03914612514526882,
+      "grad_norm": 0.19991019368171692,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.269,
+      "step": 40
+    },
+    {
+      "epoch": 0.04012477827390054,
+      "grad_norm": 0.23480480909347534,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.2437,
+      "step": 41
+    },
+    {
+      "epoch": 0.04110343140253227,
+      "grad_norm": 0.22680670022964478,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.2303,
+      "step": 42
+    },
+    {
+      "epoch": 0.04208208453116399,
+      "grad_norm": 0.24856442213058472,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.3045,
+      "step": 43
+    },
+    {
+      "epoch": 0.043060737659795706,
+      "grad_norm": 0.25991547107696533,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.2777,
+      "step": 44
+    },
+    {
+      "epoch": 0.044039390788427425,
+      "grad_norm": 0.2713627219200134,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.2902,
+      "step": 45
+    },
+    {
+      "epoch": 0.045018043917059145,
+      "grad_norm": 0.28513380885124207,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.2732,
+      "step": 46
+    },
+    {
+      "epoch": 0.04599669704569087,
+      "grad_norm": 0.31669914722442627,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.3142,
+      "step": 47
+    },
+    {
+      "epoch": 0.04697535017432259,
+      "grad_norm": 0.37770146131515503,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.3571,
+      "step": 48
+    },
+    {
+      "epoch": 0.04795400330295431,
+      "grad_norm": 0.3908044695854187,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.2915,
+      "step": 49
+    },
+    {
+      "epoch": 0.04893265643158603,
+      "grad_norm": 0.4706682562828064,
+      "learning_rate": 1e-05,
+      "loss": 2.2868,
+      "step": 50
+    },
+    {
+      "epoch": 0.04893265643158603,
+      "eval_loss": 2.397162914276123,
+      "eval_runtime": 2.0287,
+      "eval_samples_per_second": 24.647,
+      "eval_steps_per_second": 6.408,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null