Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3847e3daed3889d9ebf78c1401b8017fc8901b200a9b4049e3373c073537b4
+oid sha256:95ce6d3e1c1a5c02a31cfb280ebd213b5e203ad6f1e5087d541fb988c6262fe3
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:158026e9b29a2a38b2b22895dff3131f313d773a87317b5e8789412508cc3ffe
+oid sha256:b2e615c641240c9183ead1366f6ac4eaed7669529d56a239ceeb243d82cda1e5
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4faae14a1aa6472da1e35d90c3eeeb0dd65ba4a4be7087c6d32cacd0c607e1b
+oid sha256:1f6aaadfc3a2995ea3bff4c91194faec2c49a54ff830cb39f07c142f67055ad8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026130981544994283,
+  "epoch": 0.02939735423811857,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 187.229,
       "eval_steps_per_second": 23.458,
       "step": 40
+    },
+    {
+      "epoch": 0.027437530622243998,
+      "grad_norm": 0.08178170025348663,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9273,
+      "step": 42
+    },
+    {
+      "epoch": 0.02939735423811857,
+      "grad_norm": 0.10721062123775482,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9275,
+      "step": 45
+    },
+    {
+      "epoch": 0.02939735423811857,
+      "eval_loss": 11.927544593811035,
+      "eval_runtime": 13.7916,
+      "eval_samples_per_second": 186.925,
+      "eval_steps_per_second": 23.42,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 192833126400.0,
+  "total_flos": 216937267200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null