Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77bec1f4ac425531a05582ea8046293677e9aef7e25a09da01544099efb93f8d
+oid sha256:4b4682692992db075f9024f2c63eac83eb305915bd6c61234d4a5deca1fac75c
 size 1912664024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c62765d738accf85fc7c3f65162136ac7c75de679fcbaa389480de246257616a
+oid sha256:42f24b4f52bd0b8f9ac26e16e78879f5a8c4c27264adc49893b3fc5b8423ce1e
 size 958697812

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ab450b6ed3afea5706163f591f78b56c95466e0ef81af351a47a99261b91e2
+oid sha256:e0a61ccdb5b3252599d2e2432ba4f211122102a4126260f1358927b77c71653b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b4f26951b84f5727f8b34d9245ef840230c09420a237b4b37e336f28fe1f3c
+oid sha256:b183230938bcc01af8f0f0d377dbe65feea9f53394705c31ed6dde5c6bf91e43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.039879747223756055,
+  "epoch": 0.04294742008712191,
   "eval_steps": 20,
-  "global_step": 650,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,6 +487,51 @@
       "eval_samples_per_second": 4.261,
       "eval_steps_per_second": 0.554,
       "step": 640
+    },
+    {
+      "epoch": 0.04049328179642923,
+      "grad_norm": 0.13563913106918335,
+      "learning_rate": 0.00019196023075978888,
+      "loss": 1.4851,
+      "step": 660
+    },
+    {
+      "epoch": 0.04049328179642923,
+      "eval_loss": 1.414802074432373,
+      "eval_runtime": 23.3961,
+      "eval_samples_per_second": 4.274,
+      "eval_steps_per_second": 0.556,
+      "step": 660
+    },
+    {
+      "epoch": 0.04172035094177557,
+      "grad_norm": 0.13915061950683594,
+      "learning_rate": 0.00019171474162268321,
+      "loss": 1.4847,
+      "step": 680
+    },
+    {
+      "epoch": 0.04172035094177557,
+      "eval_loss": 1.4029760360717773,
+      "eval_runtime": 23.6066,
+      "eval_samples_per_second": 4.236,
+      "eval_steps_per_second": 0.551,
+      "step": 680
+    },
+    {
+      "epoch": 0.04294742008712191,
+      "grad_norm": 0.14418162405490875,
+      "learning_rate": 0.00019146925248557752,
+      "loss": 1.4724,
+      "step": 700
+    },
+    {
+      "epoch": 0.04294742008712191,
+      "eval_loss": 1.4029196500778198,
+      "eval_runtime": 23.5244,
+      "eval_samples_per_second": 4.251,
+      "eval_steps_per_second": 0.553,
+      "step": 700
     }
   ],
   "logging_steps": 20,
@@ -494,7 +539,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 50,
-  "total_flos": 4.730105544192e+16,
+  "total_flos": 5.08603168290816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null