Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d7473927a08af11d2835bcac04c37becbc5b8196da3a8950c56b2941400da0a
+oid sha256:ae15614e5aba83d21bbfa8fd38c5bfa8f82e6385149b49451b2e6b37df2b6d62
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:373d60bd968d84b58704d98f52a80e7de2d59d338fb9bf5cec8f34b2c53425b0
+oid sha256:ffb74839748e0a213b19efdf15c1a9fdb8c1c4f020d249bcc578ad698dadf6a0
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c1b2ac5be3cd8d07b30efc15d35a20ae097f6e09cfc422fd45d7ddd5f0c3b8
+oid sha256:28516c7cadb08fe46441ba4a0a3ee074b2b8d9dcad2789e835ca8f0d31014ca9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00807591358772461,
+  "epoch": 0.010767884783632815,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,49 @@
       "eval_samples_per_second": 8.377,
       "eval_steps_per_second": 4.191,
       "step": 15
+    },
+    {
+      "epoch": 0.008614307826906252,
+      "grad_norm": 3.1134698390960693,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.0946,
+      "step": 16
+    },
+    {
+      "epoch": 0.009152702066087893,
+      "grad_norm": 2.663564682006836,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.9865,
+      "step": 17
+    },
+    {
+      "epoch": 0.009691096305269533,
+      "grad_norm": 1.9932688474655151,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.158,
+      "step": 18
+    },
+    {
+      "epoch": 0.009691096305269533,
+      "eval_loss": 4.052786827087402,
+      "eval_runtime": 185.5821,
+      "eval_samples_per_second": 8.433,
+      "eval_steps_per_second": 4.219,
+      "step": 18
+    },
+    {
+      "epoch": 0.010229490544451174,
+      "grad_norm": 2.1913344860076904,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.1199,
+      "step": 19
+    },
+    {
+      "epoch": 0.010767884783632815,
+      "grad_norm": 2.3027989864349365,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.9268,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -179,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.300683084627968e+16,
+  "total_flos": 3.067577446170624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null