Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23835aa3baa0dcf892abf69863f1f0c1ea20a2c3908d99240a722cf7177381d0
+oid sha256:ae2287b45658d1cae69b4bfe25e777f022036e8d980148fa7635d454487588a9
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a4936925c982bfdc0019eba2398a3694957cfa3a1ee1a1b0a1af1673552c9b0
+oid sha256:556e1830f3d5b4cc26513099e09450196ba4a64ae97c75af17431421d368e625
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9927ec66b801c0f4855203d926f0323830f03e7abef37344059118107768879f
+oid sha256:4faa065a55913b65f4b0549e4d93d87e8865c0f6ec216f40a3de4d251a15322a
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319005a7acd12212946f28795d824f4aa3bb9ae8b8a8fa8426acf8d1683c7711
+oid sha256:10ae8864af9d168bc9a94e5c5625da874d35a133304d7d7414b10c80148467d4
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e15e0019059647c2b2120160188600af8acd95ba49388e85735382c6fec110
+oid sha256:ece1ed46b8aa193251efdc1d8393b3bb872b53f6ba93c31cc3efc627b34d74be
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee6bd9483dc526698ba668e9cd1c38d218e9960bb3776fb46ce2d46403967e58
+oid sha256:3018d94a8b9b3b95a3578032d80b8d3f31c01fab9a615c48039128422aba13ef
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e3c33d4b9177e702fbc3b7fe348e5bc53c0acdd468c8fa1d8d47c41439445bb
+oid sha256:d53200af24bc9fb65fd10ddaa327aeda1804119510e1de3d0cbe9297bfbcade4
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:befcb54359f53141f634f3331a650f261e163fb42877249c8517ea83d36a7124
+oid sha256:86c1416ffb6786e15b9550c111cad94cc2bc7bb18dea5ef0cdef3475e2015ab2
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d14477440f631aa977c46e3038b7d41c1e28d50b31065840e8a8470d3bdfe80
+oid sha256:47857ef45555e1fc8f192b42aa88a26a9f993ff97303b3c590fa1e726221a814
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a246be5cf8c2f6460956f9737bacb1b56ffc6195bb80d3c3d20f45b6c2226d5
+oid sha256:1912f7357d97d0c536c21d15f5ae8d134b73c487be1987df761ea730336d8216
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5197657cfe0474e002b5e477499687f2485548beb0dd654c8444eec350c0acb8
+oid sha256:74485e67705dc36efbfb69b1e54f842e1ff07894d01bb0e36d6d2526a318b300
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 66.66666666666667,
+  "epoch": 100.0,
   "eval_steps": 200,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,76 @@
       "eval_samples_per_second": 1561.466,
       "eval_steps_per_second": 6.242,
       "step": 200
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.36328125,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 9.6678,
+      "step": 210
+    },
+    {
+      "epoch": 73.33333333333333,
+      "grad_norm": 0.36328125,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 9.6641,
+      "step": 220
+    },
+    {
+      "epoch": 76.66666666666667,
+      "grad_norm": 0.36328125,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 9.6616,
+      "step": 230
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 9.6605,
+      "step": 240
+    },
+    {
+      "epoch": 83.33333333333333,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 9.6596,
+      "step": 250
+    },
+    {
+      "epoch": 86.66666666666667,
+      "grad_norm": 0.36328125,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 9.6597,
+      "step": 260
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.36328125,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 9.6595,
+      "step": 270
+    },
+    {
+      "epoch": 93.33333333333333,
+      "grad_norm": 0.361328125,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 9.6595,
+      "step": 280
+    },
+    {
+      "epoch": 96.66666666666667,
+      "grad_norm": 0.3671875,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 9.659,
+      "step": 290
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.0,
+      "loss": 9.6596,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -177,12 +247,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 327326839603200.0,
+  "total_flos": 490990259404800.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null