Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f9cc26dadbfab67fcdcf24ca55d473915fd9fcf159612d8bc29ab8542df98c6
+oid sha256:791c778d50e613af2b99c77aca642cb9aee7567880abcf258132c18df775d086
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ea2ebf1d797f49fba89cc29910756c1133507aaa323c33000cf986e901e2d5
+oid sha256:2cb76dc8f7221ff9781f9474a0e568f828e3700c7b08284ec4b9c505e19679e9
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601945f098b1f2bd868c986159372d4e79bcab90a426b1752ad18c8aed792c62
+oid sha256:558b680d20c8a456dc87962293f6d283ceca35e3120c8340321f6e2afcd6b25f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b0e37338ce3bcd7c18cd613a44b41eb72bd750902bddb4058d63cf56828fb3
+oid sha256:1c297c5cf11a27c75d9f99f1df69752f78c3ad41b0275adf50cdd1b67f9d0bb3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3157894736842105,
+  "epoch": 0.42105263157894735,
   "eval_steps": 8,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,49 @@
       "learning_rate": 0.00019937122098932428,
       "loss": 1.0046,
       "step": 15
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.30216899514198303,
+      "learning_rate": 0.00019909497617679348,
+      "loss": 1.2119,
+      "step": 16
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "eval_loss": 1.1756433248519897,
+      "eval_runtime": 2.0951,
+      "eval_samples_per_second": 47.731,
+      "eval_steps_per_second": 4.773,
+      "step": 16
+    },
+    {
+      "epoch": 0.35789473684210527,
+      "grad_norm": 0.35788360238075256,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 1.2791,
+      "step": 17
+    },
+    {
+      "epoch": 0.37894736842105264,
+      "grad_norm": 0.3098278045654297,
+      "learning_rate": 0.00019839295885986296,
+      "loss": 1.2221,
+      "step": 18
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.37158146500587463,
+      "learning_rate": 0.00019796753984232358,
+      "loss": 1.2627,
+      "step": 19
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.3635830581188202,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 1.3514,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -147,7 +190,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1496945849794560.0,
+  "total_flos": 2033729462599680.0,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null