Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248cbbd82e9755de0339732f8187bd25681cb18587f34c3a91de0c96b75a0903
+oid sha256:ee9f7eea2dd575295592ba917b24d7a282381a526cf5ec960273ae9d5f7d1300
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf99b95fd8f09b146edc1a601ec72c07d7e8d6d93d27f491cd2e1b40fbef6b3
+oid sha256:699c1a1b1e54c1590e45fffc670055a3d8522c0ae0ae5d30acf382f14654ceeb
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b8919ca363c2d41227a64b0d311c6bf7efdeaeae1142284b6297cc2caca67d
+oid sha256:11b709a6bf0fa0f36688b3f138d920bc6ad6f587da0edf35784ddb4f658162ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.413265306122449,
+  "epoch": 0.45918367346938777,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 614.721,
       "eval_steps_per_second": 156.474,
       "step": 81
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.19890524446964264,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 6.8276,
+      "step": 84
+    },
+    {
+      "epoch": 0.44387755102040816,
+      "grad_norm": 0.23790700733661652,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 6.8308,
+      "step": 87
+    },
+    {
+      "epoch": 0.45918367346938777,
+      "grad_norm": 0.22041282057762146,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 6.8293,
+      "step": 90
+    },
+    {
+      "epoch": 0.45918367346938777,
+      "eval_loss": 6.827453136444092,
+      "eval_runtime": 0.2686,
+      "eval_samples_per_second": 614.27,
+      "eval_steps_per_second": 156.36,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 778513711104.0,
+  "total_flos": 865015234560.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null