Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc89b84ff994a416b1fd8a35db8384b6b9a40381f903264827d17ecdff5f45be
+oid sha256:ddc2f6d25f763b9de0ed5430306eb636ad7c54269a7b3b70c998dbb4d0242450
 size 35668592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ffe29712d5eeee8f43f601ab13dd23dc7df7e12fb41454b57276f9b97c3680
+oid sha256:d46dc4e7f4c38bd7d740c9f5afd10a56d0c7b90d973e3e7ceaf2a89f6ab3066a
 size 18257163

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a17d91ff6dcca4633791a0e119c48601550130760f9eabb15146d59647aafb1
+oid sha256:532727a1ac4eb5b9846bd900afbac875d546089027ad66d97c611355ff543eb1
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c680537e123ff05619f00235a6bb4e1115b680be2ad94388dedf9dffc0968a0
+oid sha256:20260be3fc45a3cfa8fd6a74639f50b3b33a87c97c47f472437044dfb3488bc9
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1024392986cac23a001e3e4a426a85b67203cda9404b22609e539557db80bbac
+oid sha256:02647c16a79c538141d09a2e5ec5135201f004952aab2cef2e8f97c0a0eb658e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15043249341857842,
+  "epoch": 0.1805189921022941,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -458,6 +458,96 @@
       "mean_token_accuracy": 0.7375,
       "num_tokens": 1736202.0,
       "step": 500
+    },
+    {
+      "epoch": 0.15344114328695,
+      "grad_norm": 0.0044481828808784485,
+      "learning_rate": 2.530060120240481e-05,
+      "loss": 0.0004,
+      "mean_token_accuracy": 0.6,
+      "num_tokens": 1770561.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.15644979315532154,
+      "grad_norm": 0.0005716494051739573,
+      "learning_rate": 2.5801603206412827e-05,
+      "loss": 0.0005,
+      "mean_token_accuracy": 0.625,
+      "num_tokens": 1804749.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.1594584430236931,
+      "grad_norm": 0.00020559463882818818,
+      "learning_rate": 2.6302605210420845e-05,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.5375,
+      "num_tokens": 1839027.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.16246709289206468,
+      "grad_norm": 0.000684644328430295,
+      "learning_rate": 2.6803607214428862e-05,
+      "loss": 0.0012,
+      "mean_token_accuracy": 0.6375,
+      "num_tokens": 1872641.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.16547574276043625,
+      "grad_norm": 0.0008667957736179233,
+      "learning_rate": 2.730460921843688e-05,
+      "loss": 0.0011,
+      "mean_token_accuracy": 0.5375,
+      "num_tokens": 1908397.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.16848439262880782,
+      "grad_norm": 0.0003756976220756769,
+      "learning_rate": 2.780561122244489e-05,
+      "loss": 0.0087,
+      "mean_token_accuracy": 0.675,
+      "num_tokens": 1942186.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.1714930424971794,
+      "grad_norm": 0.0013846313813701272,
+      "learning_rate": 2.8306613226452906e-05,
+      "loss": 0.0006,
+      "mean_token_accuracy": 0.625,
+      "num_tokens": 1976984.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.17450169236555096,
+      "grad_norm": 0.0010639706160873175,
+      "learning_rate": 2.880761523046092e-05,
+      "loss": 0.0003,
+      "mean_token_accuracy": 0.6375,
+      "num_tokens": 2011487.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.17751034223392254,
+      "grad_norm": 0.002905157394707203,
+      "learning_rate": 2.9308617234468937e-05,
+      "loss": 0.0004,
+      "mean_token_accuracy": 0.5625,
+      "num_tokens": 2047066.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.1805189921022941,
+      "grad_norm": 0.0001582392433192581,
+      "learning_rate": 2.9809619238476955e-05,
+      "loss": 0.0004,
+      "mean_token_accuracy": 0.6875,
+      "num_tokens": 2081518.0,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -477,7 +567,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.887174157355008e+16,
+  "total_flos": 4.660300459087872e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null