Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0843bbbf1dd7ed15465600c90ad8c9b0c28468a0844e4ebda602129469175d
+oid sha256:cc30cece14f478e2af613381fbb617ac45fe1974313654d9fb3b322c6fce4b1e
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c151ab447f416018bacd1d65d6437793b061686c57ce2dfe2820df036bb0abc
+oid sha256:544049c4d232dccd5811f61f406354afbeb3ee63151095cf624b3182f2ab0ce4
 size 51418196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14af3b7497866f6cf5a5613385292140fe523d104121d66858d29b7a1164be40
+oid sha256:af0503fd7fbb1b552a733848d5c4fe83e7d6de89c61f8c3678e5a0147d63b66f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9a099a9106e0a8d502a4be3b996cb1e9e8205fddd096c1b15024b60866a331
+oid sha256:f7d249aebe1c6718148a5212a9c894a1a659d316ff657a708e08cb3775b5bc11
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5918367346938775,
+  "epoch": 2.877551020408163,
   "eval_steps": 7,
-  "global_step": 63,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -234,6 +234,28 @@
       "eval_samples_per_second": 22.316,
       "eval_steps_per_second": 3.188,
       "step": 63
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 1.9079219102859497,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.2447,
+      "step": 66
+    },
+    {
+      "epoch": 2.836734693877551,
+      "grad_norm": 2.1283318996429443,
+      "learning_rate": 1.4984373402728014e-06,
+      "loss": 3.9816,
+      "step": 69
+    },
+    {
+      "epoch": 2.877551020408163,
+      "eval_loss": 1.0567643642425537,
+      "eval_runtime": 1.8778,
+      "eval_samples_per_second": 22.366,
+      "eval_steps_per_second": 3.195,
+      "step": 70
     }
   ],
   "logging_steps": 3,
@@ -253,7 +275,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.642070601085747e+16,
+  "total_flos": 5.157856223428608e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null