Training in progress, step 760000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a6243c9d4d4400f2fd4b2fe0137f4acacd18bc76af280a65557307175812a8
+oid sha256:b007e5fd244b5729ff8cacaa57b1c785d03d898d5343c77b7ff241a5f8a33380
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca21d56bc23134f1ffa9773f5c9a5a5bec62d83d95ecc451f1563d89bf1ca8c7
+oid sha256:4e44d1153c2511a74df34714d54a3a947742b99b6eae06df301cfffab1c1eeb6
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d75ec6779189bfdd9065f08c6e9a994b1eb8b76967bfabdd6b27ee5e25887e
+oid sha256:120630248e0966968ea30af6ab08315c5a7b742e34d05df0eaea1327acea70ef
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d18eaa545b11ae802428fcc84a292bf166dde7d82779209b7ff66360d3f3202
+oid sha256:9ac732455f777abd748b7734f32cb802da48d17d36fc1f892d1c7b8c265c6c8d
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da273cbae47af7d864ade3a4ed313bbb87dd2d2870dcaadf34a903110facd670
-size 14439
+oid sha256:3b6effa5b718ae036f8fdfe02790dba13a4eddf18e987e06715606a6733b193f
+size 14567

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c436a8d2150800bc376a9c6d9dcefc2480a69f8f3df22480e30232f440acef23
+oid sha256:39fd70086a62614811003e1691a71dc1a1851fe2a8de8e368309da1203a65b12
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f706ed5b2c0294f08358e4528b0c33500a028d6a90aa7b815bde92b4347b626
+oid sha256:e175165a3eac134d38f788fbf76210f5cf20ad100371de72779cc7de9da4b86f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.45265472536534,
-  "global_step": 750000,
+  "epoch": 11.60535678837021,
+  "global_step": 760000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5556,11 +5556,85 @@
       "eval_samples_per_second": 1380.717,
       "eval_steps_per_second": 22.091,
       "step": 750000
+    },
+    {
+      "epoch": 11.47,
+      "learning_rate": 3.2420239909845894e-05,
+      "loss": 0.2403,
+      "step": 751000
+    },
+    {
+      "epoch": 11.48,
+      "learning_rate": 3.2250710158127045e-05,
+      "loss": 0.2402,
+      "step": 752000
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 3.2081702584991786e-05,
+      "loss": 0.2398,
+      "step": 753000
+    },
+    {
+      "epoch": 11.51,
+      "learning_rate": 3.191321903867988e-05,
+      "loss": 0.2401,
+      "step": 754000
+    },
+    {
+      "epoch": 11.53,
+      "learning_rate": 3.174526136170039e-05,
+      "loss": 0.2403,
+      "step": 755000
+    },
+    {
+      "epoch": 11.53,
+      "eval_runtime": 0.695,
+      "eval_samples_per_second": 1438.835,
+      "eval_steps_per_second": 23.021,
+      "step": 755000
+    },
+    {
+      "epoch": 11.54,
+      "learning_rate": 3.157783139081155e-05,
+      "loss": 0.24,
+      "step": 756000
+    },
+    {
+      "epoch": 11.56,
+      "learning_rate": 3.141093095700072e-05,
+      "loss": 0.2401,
+      "step": 757000
+    },
+    {
+      "epoch": 11.57,
+      "learning_rate": 3.1244561885464244e-05,
+      "loss": 0.252,
+      "step": 758000
+    },
+    {
+      "epoch": 11.59,
+      "learning_rate": 3.107872599558769e-05,
+      "loss": 0.24,
+      "step": 759000
+    },
+    {
+      "epoch": 11.61,
+      "learning_rate": 3.0913425100925795e-05,
+      "loss": 0.2396,
+      "step": 760000
+    },
+    {
+      "epoch": 11.61,
+      "eval_runtime": 0.7192,
+      "eval_samples_per_second": 1390.499,
+      "eval_steps_per_second": 22.248,
+      "step": 760000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.2575123495263995e+22,
+  "total_flos": 5.327612610556747e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca21d56bc23134f1ffa9773f5c9a5a5bec62d83d95ecc451f1563d89bf1ca8c7
+oid sha256:4e44d1153c2511a74df34714d54a3a947742b99b6eae06df301cfffab1c1eeb6
 size 449471589