Training in progress, step 336, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:addcb636d016f33a42f56c949361dc651112b44b1f3c17f4ea5d642ec2a29994
+oid sha256:acd89bab327e82c9d70eeec005795d508bf6adaacfc92ddd8f20f724469a6234
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce5eb24b6d45b8f5d21cb933ee820f15283aae75fecf2daee4b387af774d9b7
+oid sha256:bbbe25b88e42f5ce81a38f5cf504c4dcaa7e05557dd4f368b68f622afa912480
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a042cb67dc4a87fef40f9f59dff7d1a08bd46e0ddcbbd5cc8542c9d96b350b9a
+oid sha256:cd03e0f639b7da9ed1de154fce4cfdfc9d7d7afd7ed92a06fd4ed6e19dbfb56b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318b114b83c26bcba11815378a88e0015bce044b0002c702e0a2627e1a1d1e56
+oid sha256:10affc9ced28dcfaf0d40e3497a97c8e7416bd057324538f99a7e1756fd84408
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9576547231270358,
+  "epoch": 1.0944625407166124,
   "eval_steps": 42,
-  "global_step": 294,
+  "global_step": 336,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,6 +757,112 @@
       "eval_samples_per_second": 23.325,
       "eval_steps_per_second": 5.865,
       "step": 294
+    },
+    {
+      "epoch": 0.9674267100977199,
+      "grad_norm": 2.2964820861816406,
+      "learning_rate": 3.6698157721666246e-05,
+      "loss": 1.2606,
+      "step": 297
+    },
+    {
+      "epoch": 0.9771986970684039,
+      "grad_norm": 2.9193806648254395,
+      "learning_rate": 3.5773620668448384e-05,
+      "loss": 1.2477,
+      "step": 300
+    },
+    {
+      "epoch": 0.9869706840390879,
+      "grad_norm": 2.5898802280426025,
+      "learning_rate": 3.48543465876014e-05,
+      "loss": 1.2954,
+      "step": 303
+    },
+    {
+      "epoch": 0.996742671009772,
+      "grad_norm": 2.4339256286621094,
+      "learning_rate": 3.3940675559617724e-05,
+      "loss": 1.3758,
+      "step": 306
+    },
+    {
+      "epoch": 1.006514657980456,
+      "grad_norm": 2.0160953998565674,
+      "learning_rate": 3.303294559217063e-05,
+      "loss": 1.0917,
+      "step": 309
+    },
+    {
+      "epoch": 1.01628664495114,
+      "grad_norm": 2.0552120208740234,
+      "learning_rate": 3.213149249506997e-05,
+      "loss": 0.8775,
+      "step": 312
+    },
+    {
+      "epoch": 1.0260586319218241,
+      "grad_norm": 2.050333261489868,
+      "learning_rate": 3.12366497560313e-05,
+      "loss": 0.8579,
+      "step": 315
+    },
+    {
+      "epoch": 1.0358306188925082,
+      "grad_norm": 2.006868362426758,
+      "learning_rate": 3.0348748417303823e-05,
+      "loss": 0.8009,
+      "step": 318
+    },
+    {
+      "epoch": 1.0456026058631922,
+      "grad_norm": 2.201401710510254,
+      "learning_rate": 2.9468116953203107e-05,
+      "loss": 0.8379,
+      "step": 321
+    },
+    {
+      "epoch": 1.0553745928338762,
+      "grad_norm": 2.284052848815918,
+      "learning_rate": 2.8595081148593738e-05,
+      "loss": 0.7961,
+      "step": 324
+    },
+    {
+      "epoch": 1.0651465798045603,
+      "grad_norm": 2.104940414428711,
+      "learning_rate": 2.772996397836704e-05,
+      "loss": 0.8973,
+      "step": 327
+    },
+    {
+      "epoch": 1.0749185667752443,
+      "grad_norm": 2.4074976444244385,
+      "learning_rate": 2.687308548795825e-05,
+      "loss": 0.8669,
+      "step": 330
+    },
+    {
+      "epoch": 1.0846905537459284,
+      "grad_norm": 2.3930447101593018,
+      "learning_rate": 2.6024762674947313e-05,
+      "loss": 0.7428,
+      "step": 333
+    },
+    {
+      "epoch": 1.0944625407166124,
+      "grad_norm": 2.6202473640441895,
+      "learning_rate": 2.5185309371787513e-05,
+      "loss": 0.7865,
+      "step": 336
+    },
+    {
+      "epoch": 1.0944625407166124,
+      "eval_loss": 1.344246745109558,
+      "eval_runtime": 22.1704,
+      "eval_samples_per_second": 23.319,
+      "eval_steps_per_second": 5.864,
+      "step": 336
     }
   ],
   "logging_steps": 3,
@@ -776,7 +882,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2175149607564083e+17,
+  "total_flos": 2.53383140179968e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null