Training in progress, step 158000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6fe11c67454b196001e4ed79995fab7a74672309c3dd2962d5f80ffb63bc57b
+oid sha256:416215f0149ccdc8795d454a743c8eca2679e864ee093c2c92b9a7dc89d715bb
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b377b9ca632415e5cc259fc332790fb52abc8eed12ac83f3e71264ccc731be8f
+oid sha256:f007001464c0735c2a1e81f89ec3fb177e1babb5501510e4e9c8bbe36278a009
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7eb45c212b2ad29aa591c00be2416908d2afe25e585ed34f3beb9e136a92cef
+oid sha256:09a1e45eb7b9bd5bee8831d08f28097d6e76d93bacd9f185db082ca81501cddf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e7a91a2d6de7899f3ef55596029edda575e3992fc80bcaed05a5c6cf935dee
+oid sha256:30aae8d205cf2e798817f5244eb6202efaefc5672b52769c357c6911e1e312c2
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.4487226393866526,
+  "epoch": 3.4706886977079106,
   "eval_steps": 500,
-  "global_step": 157000,
+  "global_step": 158000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -27954,11 +27954,189 @@
       "eval_steps_per_second": 15.527,
       "num_input_tokens_seen": 91213822304,
       "step": 157000
+    },
+    {
+      "epoch": 3.4498209423027157,
+      "grad_norm": 0.09102839231491089,
+      "learning_rate": 0.0001,
+      "loss": 2.3407,
+      "num_input_tokens_seen": 91266251104,
+      "step": 157050
+    },
+    {
+      "epoch": 3.4509192452187785,
+      "grad_norm": 0.09813258051872253,
+      "learning_rate": 0.0001,
+      "loss": 2.3461,
+      "num_input_tokens_seen": 91318679904,
+      "step": 157100
+    },
+    {
+      "epoch": 3.452017548134841,
+      "grad_norm": 0.09532950073480606,
+      "learning_rate": 0.0001,
+      "loss": 2.3457,
+      "num_input_tokens_seen": 91371108704,
+      "step": 157150
+    },
+    {
+      "epoch": 3.4531158510509044,
+      "grad_norm": 0.10110923647880554,
+      "learning_rate": 0.0001,
+      "loss": 2.3426,
+      "num_input_tokens_seen": 91423537504,
+      "step": 157200
+    },
+    {
+      "epoch": 3.454214153966967,
+      "grad_norm": 0.09686494618654251,
+      "learning_rate": 0.0001,
+      "loss": 2.342,
+      "num_input_tokens_seen": 91475959552,
+      "step": 157250
+    },
+    {
+      "epoch": 3.4553124568830302,
+      "grad_norm": 0.09327523410320282,
+      "learning_rate": 0.0001,
+      "loss": 2.3477,
+      "num_input_tokens_seen": 91528385536,
+      "step": 157300
+    },
+    {
+      "epoch": 3.456410759799093,
+      "grad_norm": 0.10524465143680573,
+      "learning_rate": 0.0001,
+      "loss": 2.351,
+      "num_input_tokens_seen": 91580812064,
+      "step": 157350
+    },
+    {
+      "epoch": 3.4575090627151557,
+      "grad_norm": 0.08858100324869156,
+      "learning_rate": 0.0001,
+      "loss": 2.3443,
+      "num_input_tokens_seen": 91633240864,
+      "step": 157400
+    },
+    {
+      "epoch": 3.458607365631219,
+      "grad_norm": 0.0905861109495163,
+      "learning_rate": 0.0001,
+      "loss": 2.338,
+      "num_input_tokens_seen": 91685669664,
+      "step": 157450
+    },
+    {
+      "epoch": 3.4597056685472816,
+      "grad_norm": 0.0902877077460289,
+      "learning_rate": 0.0001,
+      "loss": 2.3447,
+      "num_input_tokens_seen": 91738098464,
+      "step": 157500
+    },
+    {
+      "epoch": 3.4597056685472816,
+      "eval_loss": 2.257868766784668,
+      "eval_runtime": 80.702,
+      "eval_samples_per_second": 61.956,
+      "eval_steps_per_second": 15.489,
+      "num_input_tokens_seen": 91738098464,
+      "step": 157500
+    },
+    {
+      "epoch": 3.4608039714633447,
+      "grad_norm": 0.09488774091005325,
+      "learning_rate": 0.0001,
+      "loss": 2.348,
+      "num_input_tokens_seen": 91790527264,
+      "step": 157550
+    },
+    {
+      "epoch": 3.4619022743794075,
+      "grad_norm": 0.09437818825244904,
+      "learning_rate": 0.0001,
+      "loss": 2.3366,
+      "num_input_tokens_seen": 91842955104,
+      "step": 157600
+    },
+    {
+      "epoch": 3.46300057729547,
+      "grad_norm": 0.09216772764921188,
+      "learning_rate": 0.0001,
+      "loss": 2.3455,
+      "num_input_tokens_seen": 91895383904,
+      "step": 157650
+    },
+    {
+      "epoch": 3.464098880211533,
+      "grad_norm": 0.0893646627664566,
+      "learning_rate": 0.0001,
+      "loss": 2.3436,
+      "num_input_tokens_seen": 91947812704,
+      "step": 157700
+    },
+    {
+      "epoch": 3.465197183127596,
+      "grad_norm": 0.10555808991193771,
+      "learning_rate": 0.0001,
+      "loss": 2.3407,
+      "num_input_tokens_seen": 92000241504,
+      "step": 157750
+    },
+    {
+      "epoch": 3.466295486043659,
+      "grad_norm": 0.09263647347688675,
+      "learning_rate": 0.0001,
+      "loss": 2.3455,
+      "num_input_tokens_seen": 92052667776,
+      "step": 157800
+    },
+    {
+      "epoch": 3.467393788959722,
+      "grad_norm": 0.09790777415037155,
+      "learning_rate": 0.0001,
+      "loss": 2.3426,
+      "num_input_tokens_seen": 92105094528,
+      "step": 157850
+    },
+    {
+      "epoch": 3.4684920918757847,
+      "grad_norm": 0.0883532464504242,
+      "learning_rate": 0.0001,
+      "loss": 2.3453,
+      "num_input_tokens_seen": 92157523328,
+      "step": 157900
+    },
+    {
+      "epoch": 3.4695903947918474,
+      "grad_norm": 0.09379395842552185,
+      "learning_rate": 0.0001,
+      "loss": 2.3452,
+      "num_input_tokens_seen": 92209949248,
+      "step": 157950
+    },
+    {
+      "epoch": 3.4706886977079106,
+      "grad_norm": 0.09533659368753433,
+      "learning_rate": 0.0001,
+      "loss": 2.3454,
+      "num_input_tokens_seen": 92262378048,
+      "step": 158000
+    },
+    {
+      "epoch": 3.4706886977079106,
+      "eval_loss": 2.258249521255493,
+      "eval_runtime": 80.6484,
+      "eval_samples_per_second": 61.998,
+      "eval_steps_per_second": 15.499,
+      "num_input_tokens_seen": 92262378048,
+      "step": 158000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 91213822304,
+  "num_input_tokens_seen": 92262378048,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -27973,7 +28151,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.614318280768918e+20,
+  "total_flos": 1.632875804872041e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null