Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f84e7b63436671da375a41d5bbf5e1239f4c8aec811167813a8bf31b1ced550
+oid sha256:985be99f2fe51d4234f4b22a7f33c60445325ad03f922ee402fee4140b72158f
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215b2efb297e43e0b0bd6527f407a3a1c19dabcbcffd428b261c614017f3386c
+oid sha256:4dade84db92ba85badc3b2e0f25466951d10090f7ecd0530ee00a0033bce3374
 size 591203178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
+oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d264ea2b31efc6175c9b88c292060b1e331f84753196c51fa4b1c3c0bd9a5f38
+oid sha256:b14cbd30fe629fc4c294758d371dfad4518c573c64f4a435e9760f96ef5a4526
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4918032786885246,
+  "epoch": 0.6557377049180327,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,84 @@
       "eval_samples_per_second": 1.092,
       "eval_steps_per_second": 1.092,
       "step": 300
+    },
+    {
+      "epoch": 0.5081967213114754,
+      "grad_norm": 0.734933614730835,
+      "learning_rate": 5.7270183690184495e-05,
+      "loss": 0.1585,
+      "step": 310
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 0.8497341275215149,
+      "learning_rate": 5.4429040348292256e-05,
+      "loss": 0.1406,
+      "step": 320
+    },
+    {
+      "epoch": 0.5409836065573771,
+      "grad_norm": 0.8217471241950989,
+      "learning_rate": 5.157339773500125e-05,
+      "loss": 0.1388,
+      "step": 330
+    },
+    {
+      "epoch": 0.5573770491803278,
+      "grad_norm": 0.3617191016674042,
+      "learning_rate": 4.8712604317250576e-05,
+      "loss": 0.1493,
+      "step": 340
+    },
+    {
+      "epoch": 0.5737704918032787,
+      "grad_norm": 0.9715378880500793,
+      "learning_rate": 4.585602542407722e-05,
+      "loss": 0.1446,
+      "step": 350
+    },
+    {
+      "epoch": 0.5901639344262295,
+      "grad_norm": 0.8967556953430176,
+      "learning_rate": 4.3013012587503254e-05,
+      "loss": 0.1134,
+      "step": 360
+    },
+    {
+      "epoch": 0.6065573770491803,
+      "grad_norm": 1.1487077474594116,
+      "learning_rate": 4.019287292859016e-05,
+      "loss": 0.1419,
+      "step": 370
+    },
+    {
+      "epoch": 0.6229508196721312,
+      "grad_norm": 0.8955410718917847,
+      "learning_rate": 3.7404838688880446e-05,
+      "loss": 0.1339,
+      "step": 380
+    },
+    {
+      "epoch": 0.639344262295082,
+      "grad_norm": 0.7369993925094604,
+      "learning_rate": 3.465803700697114e-05,
+      "loss": 0.1435,
+      "step": 390
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 0.4338698089122772,
+      "learning_rate": 3.196146003916084e-05,
+      "loss": 0.1423,
+      "step": 400
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "eval_loss": 0.13493812084197998,
+      "eval_runtime": 62.3222,
+      "eval_samples_per_second": 1.091,
+      "eval_steps_per_second": 1.091,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -260,7 +338,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5636040300257280.0,
+  "total_flos": 7442719869788160.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null