Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83c968deb955f60eb9e41629446edce80585eb2cf1d73553a8a979604a23679
+oid sha256:fb5236b6827bef341df072bb7fdd98ce664b6bed0b62ab62b5164a15550697ef
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97794de34031b842712dbdab4852564354f523240bfd970f18bb6131da726eb6
+oid sha256:10eaa17c3c36b2aac94e2f525dfb20e289c3847b94b83446bb5db9f3cf3a42ca
 size 54405050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833a9149efbd02f69cacb86bd651317733ce9a17e61a32699f883f458a39befb
+oid sha256:6e3cabeeaeee334db7069a918c4c440841cc12b8cd67abcbfed74e79ad63261b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032938076416337285,
+  "epoch": 0.004940711462450593,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 93.178,
       "eval_steps_per_second": 46.589,
       "step": 50
+    },
+    {
+      "epoch": 0.0033596837944664033,
+      "grad_norm": 24.591201782226562,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.4161,
+      "step": 51
+    },
+    {
+      "epoch": 0.0034255599472990776,
+      "grad_norm": 25.71407127380371,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 1.8524,
+      "step": 52
+    },
+    {
+      "epoch": 0.0034914361001317524,
+      "grad_norm": 11.431339263916016,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 1.3038,
+      "step": 53
+    },
+    {
+      "epoch": 0.0035573122529644267,
+      "grad_norm": 4.827043056488037,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9158,
+      "step": 54
+    },
+    {
+      "epoch": 0.0036231884057971015,
+      "grad_norm": 4.436622142791748,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.965,
+      "step": 55
+    },
+    {
+      "epoch": 0.003689064558629776,
+      "grad_norm": 4.050058841705322,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.8211,
+      "step": 56
+    },
+    {
+      "epoch": 0.0037549407114624506,
+      "grad_norm": 3.1016499996185303,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7529,
+      "step": 57
+    },
+    {
+      "epoch": 0.0038208168642951254,
+      "grad_norm": 4.726005554199219,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.8557,
+      "step": 58
+    },
+    {
+      "epoch": 0.0038866930171277997,
+      "grad_norm": 2.214892864227295,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.7175,
+      "step": 59
+    },
+    {
+      "epoch": 0.003952569169960474,
+      "grad_norm": 4.246845722198486,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7439,
+      "step": 60
+    },
+    {
+      "epoch": 0.004018445322793149,
+      "grad_norm": 4.392334938049316,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.6842,
+      "step": 61
+    },
+    {
+      "epoch": 0.004084321475625824,
+      "grad_norm": 3.2064085006713867,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.6525,
+      "step": 62
+    },
+    {
+      "epoch": 0.004150197628458498,
+      "grad_norm": 1.4928427934646606,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6628,
+      "step": 63
+    },
+    {
+      "epoch": 0.004216073781291172,
+      "grad_norm": 1.9086092710494995,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.5528,
+      "step": 64
+    },
+    {
+      "epoch": 0.004281949934123847,
+      "grad_norm": 1.587053894996643,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.6403,
+      "step": 65
+    },
+    {
+      "epoch": 0.004347826086956522,
+      "grad_norm": 1.581070065498352,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6374,
+      "step": 66
+    },
+    {
+      "epoch": 0.0044137022397891966,
+      "grad_norm": 1.8241552114486694,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.5657,
+      "step": 67
+    },
+    {
+      "epoch": 0.0044795783926218705,
+      "grad_norm": 1.4631158113479614,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.5628,
+      "step": 68
+    },
+    {
+      "epoch": 0.004545454545454545,
+      "grad_norm": 1.8254574537277222,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5396,
+      "step": 69
+    },
+    {
+      "epoch": 0.00461133069828722,
+      "grad_norm": 2.219564199447632,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.6934,
+      "step": 70
+    },
+    {
+      "epoch": 0.004677206851119895,
+      "grad_norm": 2.0074427127838135,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.6174,
+      "step": 71
+    },
+    {
+      "epoch": 0.0047430830039525695,
+      "grad_norm": 1.820469617843628,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5807,
+      "step": 72
+    },
+    {
+      "epoch": 0.0048089591567852434,
+      "grad_norm": 1.49021577835083,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.5769,
+      "step": 73
+    },
+    {
+      "epoch": 0.004874835309617918,
+      "grad_norm": 2.088482141494751,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.7059,
+      "step": 74
+    },
+    {
+      "epoch": 0.004940711462450593,
+      "grad_norm": 4.479631423950195,
+      "learning_rate": 0.0,
+      "loss": 0.9487,
+      "step": 75
+    },
+    {
+      "epoch": 0.004940711462450593,
+      "eval_loss": 0.7876570820808411,
+      "eval_runtime": 137.1521,
+      "eval_samples_per_second": 93.21,
+      "eval_steps_per_second": 46.605,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1428824122195968.0,
+  "total_flos": 2146790472155136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null