Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b8a05354bfc115960dd16218e1ebb70714a6d58cf36c6dfcbb59abbf712ee6c
+oid sha256:60a8151bee68255d9064bbfdc2170764612ef8d251c1027fa3d7f12321916dbc
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789221ac653e4b18a53f5043ec5c3993652f6e86b04a6c8b6fa2041e24213b49
+oid sha256:40239a22d776e1fb8b4210a19644be230adf89378f030068f6bdc92cdbebfd01
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1791dcc0c8e5d9192b7663e1b585ff1dccd113452a5e1d1cca250b5164d37cb8
+oid sha256:67e8fb856d223a5af24cc75d2aa8b4de37cdfc3cbf75d495b03ac0cbca8dbef4
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52002c03f9e92e22821e4d80f4cf803ea1f4727e756138e319ab19f9be28c22e
+oid sha256:c15dd75d8ac97bb6e7d4107e91cba13385d6d6961fc51bf55911773daaa9d375
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.997206530510894,
+  "epoch": 5.997206530510894,
   "eval_steps": 50,
-  "global_step": 1255,
+  "global_step": 1506,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -382,6 +382,81 @@
       "eval_samples_per_second": 57.986,
       "eval_steps_per_second": 28.993,
       "step": 1250
+    },
+    {
+      "epoch": 5.17878204730275,
+      "grad_norm": 1.1285374164581299,
+      "learning_rate": 4.820717131474104e-05,
+      "loss": 1.0088,
+      "step": 1300
+    },
+    {
+      "epoch": 5.17878204730275,
+      "eval_loss": 1.0875197649002075,
+      "eval_runtime": 14.7256,
+      "eval_samples_per_second": 57.587,
+      "eval_steps_per_second": 28.793,
+      "step": 1300
+    },
+    {
+      "epoch": 5.377428766528028,
+      "grad_norm": 0.9647625684738159,
+      "learning_rate": 4.6215139442231074e-05,
+      "loss": 1.0,
+      "step": 1350
+    },
+    {
+      "epoch": 5.377428766528028,
+      "eval_loss": 1.0778887271881104,
+      "eval_runtime": 14.6228,
+      "eval_samples_per_second": 57.992,
+      "eval_steps_per_second": 28.996,
+      "step": 1350
+    },
+    {
+      "epoch": 5.5760754857533055,
+      "grad_norm": 1.074511170387268,
+      "learning_rate": 4.4223107569721116e-05,
+      "loss": 0.9925,
+      "step": 1400
+    },
+    {
+      "epoch": 5.5760754857533055,
+      "eval_loss": 1.0578875541687012,
+      "eval_runtime": 14.6013,
+      "eval_samples_per_second": 58.077,
+      "eval_steps_per_second": 29.038,
+      "step": 1400
+    },
+    {
+      "epoch": 5.774722204978583,
+      "grad_norm": 0.999279797077179,
+      "learning_rate": 4.223107569721116e-05,
+      "loss": 0.9831,
+      "step": 1450
+    },
+    {
+      "epoch": 5.774722204978583,
+      "eval_loss": 1.068110466003418,
+      "eval_runtime": 14.6065,
+      "eval_samples_per_second": 58.056,
+      "eval_steps_per_second": 29.028,
+      "step": 1450
+    },
+    {
+      "epoch": 5.973368924203861,
+      "grad_norm": 1.027130126953125,
+      "learning_rate": 4.02390438247012e-05,
+      "loss": 0.9744,
+      "step": 1500
+    },
+    {
+      "epoch": 5.973368924203861,
+      "eval_loss": 1.0516407489776611,
+      "eval_runtime": 14.5827,
+      "eval_samples_per_second": 58.151,
+      "eval_steps_per_second": 29.076,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -401,7 +476,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0033664206870938e+17,
+  "total_flos": 2.404255336140636e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null