Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b0a9ddfee0836ce999045e37984c53e1fd5db5723d2c234bb526f71266b9a3a
+oid sha256:f23450359fdb07ebcd0caa0b3b757cc7ebb632d49851262494267f85df9b75f9
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3dedfad9b182a8043dfff409080c3e2610386a02849bc00bdf2b07c11fabec5
+oid sha256:968db29b6bed2f48495b5e4b3842813ade8836d75e6e318a78f20b3c4b192404
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e270735a79923e0c6166ab5b689b246abcdff7e078e01068f6374acfd7f47f1c
+oid sha256:a6f5fe99d81e7517b5957d450f6702d8ebbd0807e19095a89194ae9f341f65dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b52924c88c1c80163d374a6650253dd74b8b46052a3da6fc5e4076e57b5effa
+oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004307153913453126,
+  "epoch": 0.0053839423918164075,
   "eval_steps": 4,
-  "global_step": 16,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -159,6 +159,42 @@
       "eval_samples_per_second": 8.369,
       "eval_steps_per_second": 4.187,
       "step": 16
+    },
+    {
+      "epoch": 0.004576351033043946,
+      "grad_norm": 3.4099552631378174,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 4.133,
+      "step": 17
+    },
+    {
+      "epoch": 0.004845548152634767,
+      "grad_norm": 3.074971914291382,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.9521,
+      "step": 18
+    },
+    {
+      "epoch": 0.005114745272225587,
+      "grad_norm": 2.5733466148376465,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 4.1701,
+      "step": 19
+    },
+    {
+      "epoch": 0.0053839423918164075,
+      "grad_norm": 3.7706105709075928,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.9503,
+      "step": 20
+    },
+    {
+      "epoch": 0.0053839423918164075,
+      "eval_loss": 4.0563483238220215,
+      "eval_runtime": 187.0013,
+      "eval_samples_per_second": 8.369,
+      "eval_steps_per_second": 4.187,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -178,7 +214,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2270309784682496e+16,
+  "total_flos": 1.533788723085312e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null