Training in progress, step 440000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f901372af6bb5b8376fb0e8c20402718b44a70119bbfac36dcede9e02013f02
+oid sha256:35d81de4abe2a01fcba75c50c9cab620ae3a65b0f95ffcc3a534ae9481509bf9
 size 995605445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68bd329f4168f6dda7d79fde6f824423ece665c87015507338729a29734782dc
+oid sha256:58855d5f2b4933bc7ddfa06dc9f27291b7fece9d81c961cb18c4fbd189f9d2b6
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2d1c20de5c0b926a7cd672fd77f7fbe7fbc7338cfbe0b012185d341668909e
+oid sha256:afb4822acf65cc3a55faa6756d51c5357c415e3967748bd0784d6c7fc546fb6f
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.180888341699024,
-  "global_step": 430000,
+  "epoch": 10.417653186854816,
+  "global_step": 440000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5516,11 +5516,139 @@
       "eval_samples_per_second": 166.474,
       "eval_steps_per_second": 20.814,
       "step": 430000
+    },
+    {
+      "epoch": 10.19,
+      "learning_rate": 0.0,
+      "loss": 2.414,
+      "step": 430500
+    },
+    {
+      "epoch": 10.2,
+      "learning_rate": 0.0,
+      "loss": 2.4156,
+      "step": 431000
+    },
+    {
+      "epoch": 10.22,
+      "learning_rate": 0.0,
+      "loss": 2.4344,
+      "step": 431500
+    },
+    {
+      "epoch": 10.23,
+      "learning_rate": 0.0,
+      "loss": 2.4329,
+      "step": 432000
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 0.0,
+      "loss": 2.43,
+      "step": 432500
+    },
+    {
+      "epoch": 10.25,
+      "learning_rate": 0.0,
+      "loss": 2.421,
+      "step": 433000
+    },
+    {
+      "epoch": 10.26,
+      "learning_rate": 0.0,
+      "loss": 2.445,
+      "step": 433500
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 0.0,
+      "loss": 2.4289,
+      "step": 434000
+    },
+    {
+      "epoch": 10.29,
+      "learning_rate": 0.0,
+      "loss": 2.4156,
+      "step": 434500
+    },
+    {
+      "epoch": 10.3,
+      "learning_rate": 0.0,
+      "loss": 2.4156,
+      "step": 435000
+    },
+    {
+      "epoch": 10.31,
+      "learning_rate": 0.0,
+      "loss": 2.4323,
+      "step": 435500
+    },
+    {
+      "epoch": 10.32,
+      "learning_rate": 0.0,
+      "loss": 2.4255,
+      "step": 436000
+    },
+    {
+      "epoch": 10.33,
+      "learning_rate": 0.0,
+      "loss": 2.4298,
+      "step": 436500
+    },
+    {
+      "epoch": 10.35,
+      "learning_rate": 0.0,
+      "loss": 2.4263,
+      "step": 437000
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 0.0,
+      "loss": 2.4381,
+      "step": 437500
+    },
+    {
+      "epoch": 10.37,
+      "learning_rate": 0.0,
+      "loss": 2.4327,
+      "step": 438000
+    },
+    {
+      "epoch": 10.38,
+      "learning_rate": 0.0,
+      "loss": 2.4352,
+      "step": 438500
+    },
+    {
+      "epoch": 10.39,
+      "learning_rate": 0.0,
+      "loss": 2.4329,
+      "step": 439000
+    },
+    {
+      "epoch": 10.41,
+      "learning_rate": 0.0,
+      "loss": 2.4273,
+      "step": 439500
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 0.0,
+      "loss": 2.4106,
+      "step": 440000
+    },
+    {
+      "epoch": 10.42,
+      "eval_loss": 3.1522228717803955,
+      "eval_runtime": 112.8716,
+      "eval_samples_per_second": 166.313,
+      "eval_steps_per_second": 20.794,
+      "step": 440000
     }
   ],
   "max_steps": 633540,
   "num_train_epochs": 15,
-  "total_flos": 9.0761179511808e+16,
+  "total_flos": 9.2865123366912e+16,
   "trial_name": null,
   "trial_params": null
 }