Training in progress, step 670000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1b9c3dadef4c83eaa6444ae31d8e46ec85073c61b37dd61844f05913236e16
+oid sha256:965860eaf3c3ea343e75b1d82190f39b5bb62e76f36d4448a6618790db6ff870
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fc5b645a51764da4f8ff98e3c407a8e3b54b7f2ebf4044514e81a387a44685
+oid sha256:5578b4d4e33e87af6d4056fd17ea4c7b1d31f9e365318710f084d9f8ad6a9e7a
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc9f2d6c7b188b0a4e60257b0a8bd84c335d50dfde13a7917d3ec48da9a1694
+oid sha256:6e83b18565bb157c89e4103ebdca556e5a6af6a5fd5614439ee11638b091ec95
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f55bf132d9f9827e3128928d8dd16bab60642cd4846a79818e1304f0d9048138
+oid sha256:413c5c9b29f5423e3974277660424767e4053296a5d316f7bd214cca3e9c3452
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c250144fe49ffdfe7647f695a0d687d07a9a35cdce7fa106343ed4f42beb24af
+oid sha256:027e092b1b60566b466a15ddaa84a08bd53806c1b3cde5871142648013620d30
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d99a97fa7df68e7130dee285dc72156e57930a619ecb49b136dff7611919aa2
-size 14439
+oid sha256:20f44ecad91e276e5983fd17d83f87c8abed938c6303227829dce7483dd60c92
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e668d5f010f36e9bc3681300c074ae1cd82ec8d3466f5c0bcb0eb7c6db53f6b
+oid sha256:651f855ada6fd7cfa09b534ad266032caacaa52b90009ef1696c08e67fbed919
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.078336158321498,
-  "global_step": 660000,
+  "epoch": 10.23103822132637,
+  "global_step": 670000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4890,11 +4890,85 @@
       "eval_samples_per_second": 957.361,
       "eval_steps_per_second": 15.318,
       "step": 660000
+    },
+    {
+      "epoch": 10.09,
+      "learning_rate": 4.956856283426728e-05,
+      "loss": 0.2487,
+      "step": 661000
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 4.936026312555037e-05,
+      "loss": 0.248,
+      "step": 662000
+    },
+    {
+      "epoch": 10.12,
+      "learning_rate": 4.915229848808698e-05,
+      "loss": 0.2478,
+      "step": 663000
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 4.8944671196145136e-05,
+      "loss": 0.2484,
+      "step": 664000
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 4.8737383520303546e-05,
+      "loss": 0.2485,
+      "step": 665000
+    },
+    {
+      "epoch": 10.15,
+      "eval_runtime": 1.1085,
+      "eval_samples_per_second": 902.106,
+      "eval_steps_per_second": 14.434,
+      "step": 665000
+    },
+    {
+      "epoch": 10.17,
+      "learning_rate": 4.853043772742709e-05,
+      "loss": 0.248,
+      "step": 666000
+    },
+    {
+      "epoch": 10.19,
+      "learning_rate": 4.832383608064172e-05,
+      "loss": 0.2476,
+      "step": 667000
+    },
+    {
+      "epoch": 10.2,
+      "learning_rate": 4.811758083931005e-05,
+      "loss": 0.2478,
+      "step": 668000
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 4.791167425900632e-05,
+      "loss": 0.2481,
+      "step": 669000
+    },
+    {
+      "epoch": 10.23,
+      "learning_rate": 4.770611859149185e-05,
+      "loss": 0.2508,
+      "step": 670000
+    },
+    {
+      "epoch": 10.23,
+      "eval_runtime": 1.1412,
+      "eval_samples_per_second": 876.243,
+      "eval_steps_per_second": 14.02,
+      "step": 670000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.626610657321424e+22,
+  "total_flos": 4.696710918351771e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fc5b645a51764da4f8ff98e3c407a8e3b54b7f2ebf4044514e81a387a44685
+oid sha256:5578b4d4e33e87af6d4056fd17ea4c7b1d31f9e365318710f084d9f8ad6a9e7a
 size 449471589