Training in progress, step 750000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0b6142827a79f5d4b326c8ef95883604994380c09564cc48d7c1a0eecc0ae0c
+oid sha256:06a6243c9d4d4400f2fd4b2fe0137f4acacd18bc76af280a65557307175812a8
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b5410b91904505f995b54f8dbaf35031127f48559f667a312bfe26edbdc46c
+oid sha256:ca21d56bc23134f1ffa9773f5c9a5a5bec62d83d95ecc451f1563d89bf1ca8c7
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d16bcb150fb723167f32e28532d305d9b788035b9c1c04eefc4171601b8a86cf
+oid sha256:33d75ec6779189bfdd9065f08c6e9a994b1eb8b76967bfabdd6b27ee5e25887e
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f68eb57082d644a52febc0af19784501f7d94576defdbcf673807dd01942a834
+oid sha256:1d18eaa545b11ae802428fcc84a292bf166dde7d82779209b7ff66360d3f3202
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e011812af607ddca2f8883a544e1029094dd30ea8f434fd3b69dea782324c8
-size 14503
+oid sha256:da273cbae47af7d864ade3a4ed313bbb87dd2d2870dcaadf34a903110facd670
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac4fa903420068a2c49e97bb4ec5079f04b5e57b740f4f724d3e2eb49716420
+oid sha256:c436a8d2150800bc376a9c6d9dcefc2480a69f8f3df22480e30232f440acef23
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9f0f128872a454b4739c6d1bc039a16d454358b055fa818e1343bc269f4881
+oid sha256:3f706ed5b2c0294f08358e4528b0c33500a028d6a90aa7b815bde92b4347b626
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.299952662360468,
-  "global_step": 740000,
+  "epoch": 11.45265472536534,
+  "global_step": 750000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5482,11 +5482,85 @@
       "eval_samples_per_second": 1289.598,
       "eval_steps_per_second": 20.634,
       "step": 740000
+    },
+    {
+      "epoch": 11.32,
+      "learning_rate": 3.4143846579608744e-05,
+      "loss": 0.2411,
+      "step": 741000
+    },
+    {
+      "epoch": 11.33,
+      "learning_rate": 3.396919794145629e-05,
+      "loss": 0.2412,
+      "step": 742000
+    },
+    {
+      "epoch": 11.35,
+      "learning_rate": 3.3795052688780345e-05,
+      "loss": 0.241,
+      "step": 743000
+    },
+    {
+      "epoch": 11.36,
+      "learning_rate": 3.362141272600552e-05,
+      "loss": 0.2413,
+      "step": 744000
+    },
+    {
+      "epoch": 11.38,
+      "learning_rate": 3.3448279952030615e-05,
+      "loss": 0.241,
+      "step": 745000
+    },
+    {
+      "epoch": 11.38,
+      "eval_runtime": 0.937,
+      "eval_samples_per_second": 1067.221,
+      "eval_steps_per_second": 17.076,
+      "step": 745000
+    },
+    {
+      "epoch": 11.39,
+      "learning_rate": 3.327565626020793e-05,
+      "loss": 0.2408,
+      "step": 746000
+    },
+    {
+      "epoch": 11.41,
+      "learning_rate": 3.3103543538322455e-05,
+      "loss": 0.2408,
+      "step": 747000
+    },
+    {
+      "epoch": 11.42,
+      "learning_rate": 3.293194366857137e-05,
+      "loss": 0.2407,
+      "step": 748000
+    },
+    {
+      "epoch": 11.44,
+      "learning_rate": 3.276085852754336e-05,
+      "loss": 0.2409,
+      "step": 749000
+    },
+    {
+      "epoch": 11.45,
+      "learning_rate": 3.259028998619814e-05,
+      "loss": 0.2405,
+      "step": 750000
+    },
+    {
+      "epoch": 11.45,
+      "eval_runtime": 0.7243,
+      "eval_samples_per_second": 1380.717,
+      "eval_steps_per_second": 22.091,
+      "step": 750000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.187412088496052e+22,
+  "total_flos": 5.2575123495263995e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b5410b91904505f995b54f8dbaf35031127f48559f667a312bfe26edbdc46c
+oid sha256:ca21d56bc23134f1ffa9773f5c9a5a5bec62d83d95ecc451f1563d89bf1ca8c7
 size 449471589