Training in progress, step 670000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aad0df180d03ae210e89f44f0cac635fabb878b717d01bd82a81c726ae27d91
+oid sha256:890198f678ba65d216debb2bc86f4ae914eacfa0277bfe9ecb7d160986d858d3
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0bfba03f58cbdd9d57a0f2311fd1afee4de225070f727170c4561c7ba75d7d
+oid sha256:fc3bbdcfad15508d1c6487b56498c528da76f45271d070de2c2ce847ed3bd008
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d75e5bb71e022d56ffb8c3dda9b05cd9d4614f8a1b736aba397a27b096cdee0
+oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d75e5bb71e022d56ffb8c3dda9b05cd9d4614f8a1b736aba397a27b096cdee0
+oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d75e5bb71e022d56ffb8c3dda9b05cd9d4614f8a1b736aba397a27b096cdee0
+oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d75e5bb71e022d56ffb8c3dda9b05cd9d4614f8a1b736aba397a27b096cdee0
+oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d75e5bb71e022d56ffb8c3dda9b05cd9d4614f8a1b736aba397a27b096cdee0
+oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d75e5bb71e022d56ffb8c3dda9b05cd9d4614f8a1b736aba397a27b096cdee0
+oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d75e5bb71e022d56ffb8c3dda9b05cd9d4614f8a1b736aba397a27b096cdee0
+oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d75e5bb71e022d56ffb8c3dda9b05cd9d4614f8a1b736aba397a27b096cdee0
+oid sha256:b717cf04a53175defa6ff5aaf7e033bb060ce4d493175abed3dd7b6e89cbdd38
 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": 7.003758518006313,
-  "global_step": 660000,
+  "epoch": 7.115287242229236,
+  "global_step": 670000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -13206,11 +13206,211 @@
       "eval_samples_per_second": 870.836,
       "eval_steps_per_second": 13.648,
       "step": 660000
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 4.967283762863444e-05,
+      "loss": 0.1974,
+      "step": 660500
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 4.956856283426728e-05,
+      "loss": 0.1972,
+      "step": 661000
+    },
+    {
+      "epoch": 7.01,
+      "eval_loss": 0.18715223670005798,
+      "eval_runtime": 2.6628,
+      "eval_samples_per_second": 862.627,
+      "eval_steps_per_second": 13.52,
+      "step": 661000
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 4.946437123828732e-05,
+      "loss": 0.1971,
+      "step": 661500
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 4.936026312555037e-05,
+      "loss": 0.1967,
+      "step": 662000
+    },
+    {
+      "epoch": 7.03,
+      "eval_loss": 0.18600988388061523,
+      "eval_runtime": 2.614,
+      "eval_samples_per_second": 878.714,
+      "eval_steps_per_second": 13.772,
+      "step": 662000
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 4.925623878068408e-05,
+      "loss": 0.1972,
+      "step": 662500
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 4.915229848808698e-05,
+      "loss": 0.1973,
+      "step": 663000
+    },
+    {
+      "epoch": 7.04,
+      "eval_loss": 0.1860048770904541,
+      "eval_runtime": 2.673,
+      "eval_samples_per_second": 859.331,
+      "eval_steps_per_second": 13.468,
+      "step": 663000
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 4.904844253192795e-05,
+      "loss": 0.1965,
+      "step": 663500
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 4.8944671196145136e-05,
+      "loss": 0.1967,
+      "step": 664000
+    },
+    {
+      "epoch": 7.05,
+      "eval_loss": 0.18750624358654022,
+      "eval_runtime": 2.7099,
+      "eval_samples_per_second": 847.62,
+      "eval_steps_per_second": 13.284,
+      "step": 664000
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 4.884098476444539e-05,
+      "loss": 0.1968,
+      "step": 664500
+    },
+    {
+      "epoch": 7.06,
+      "learning_rate": 4.8737383520303546e-05,
+      "loss": 0.1965,
+      "step": 665000
+    },
+    {
+      "epoch": 7.06,
+      "eval_loss": 0.18656140565872192,
+      "eval_runtime": 2.728,
+      "eval_samples_per_second": 842.009,
+      "eval_steps_per_second": 13.196,
+      "step": 665000
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 4.8633867746961356e-05,
+      "loss": 0.1968,
+      "step": 665500
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 4.853043772742709e-05,
+      "loss": 0.1969,
+      "step": 666000
+    },
+    {
+      "epoch": 7.07,
+      "eval_loss": 0.18721851706504822,
+      "eval_runtime": 2.6334,
+      "eval_samples_per_second": 872.245,
+      "eval_steps_per_second": 13.67,
+      "step": 666000
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 4.8427093744474364e-05,
+      "loss": 0.1971,
+      "step": 666500
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 4.832383608064172e-05,
+      "loss": 0.1968,
+      "step": 667000
+    },
+    {
+      "epoch": 7.08,
+      "eval_loss": 0.18801318109035492,
+      "eval_runtime": 2.7526,
+      "eval_samples_per_second": 834.477,
+      "eval_steps_per_second": 13.078,
+      "step": 667000
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 4.822066501823172e-05,
+      "loss": 0.1967,
+      "step": 667500
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 4.811758083931005e-05,
+      "loss": 0.1967,
+      "step": 668000
+    },
+    {
+      "epoch": 7.09,
+      "eval_loss": 0.18405194580554962,
+      "eval_runtime": 2.6183,
+      "eval_samples_per_second": 877.299,
+      "eval_steps_per_second": 13.75,
+      "step": 668000
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 4.8014583825704976e-05,
+      "loss": 0.1965,
+      "step": 668500
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 4.791167425900632e-05,
+      "loss": 0.1968,
+      "step": 669000
+    },
+    {
+      "epoch": 7.1,
+      "eval_loss": 0.18537673354148865,
+      "eval_runtime": 2.6514,
+      "eval_samples_per_second": 866.335,
+      "eval_steps_per_second": 13.578,
+      "step": 669000
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 4.780885242056493e-05,
+      "loss": 0.1963,
+      "step": 669500
+    },
+    {
+      "epoch": 7.12,
+      "learning_rate": 4.770611859149185e-05,
+      "loss": 0.1963,
+      "step": 670000
+    },
+    {
+      "epoch": 7.12,
+      "eval_loss": 0.187167689204216,
+      "eval_runtime": 2.6705,
+      "eval_samples_per_second": 860.127,
+      "eval_steps_per_second": 13.48,
+      "step": 670000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 4.626578892870302e+22,
+  "total_flos": 4.696679153900649e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0bfba03f58cbdd9d57a0f2311fd1afee4de225070f727170c4561c7ba75d7d
+oid sha256:fc3bbdcfad15508d1c6487b56498c528da76f45271d070de2c2ce847ed3bd008
 size 449471589