Training in progress, step 140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2693e3c807ab1261a91352b2a34141c7debf3c87e07888e0213731c63bf1238c
+oid sha256:11ddbf41eaaa839589f1095623d71d7b903fb219c74e298e1719200dfd47b771
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d38d2f83edf7948b193d522722e03c4f2b8cbed5067da59897c7f7c3822919
+oid sha256:b5ce0623a30bd01e5e27495816869c88c33b4cb28c0d789da7326c5b2ec46c6d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79354fda314c9103e2d55f6fd0e3e7ec5fe801812e33d2c8e4dd8c180772e09a
+oid sha256:ad528149b7ddaf36aa54c3270bc91600bfb527af6fb344cfc62207a9548bc407
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc750a6dfb3e5c9f642238b7443b0984a56e79b7c2731a6e152ecfc3e32f4e7
+oid sha256:671828e69cd8fd42106344a5797cbc78f701a434a6386d9dfacd16451ba179aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06601870529983496,
+  "epoch": 0.06846384253316218,
   "eval_steps": 34,
-  "global_step": 135,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -984,6 +984,49 @@
       "learning_rate": 6.387583338128471e-05,
       "loss": 1.1751,
       "step": 135
+    },
+    {
+      "epoch": 0.0665077327465004,
+      "grad_norm": 0.3435130715370178,
+      "learning_rate": 6.215889499576898e-05,
+      "loss": 1.0164,
+      "step": 136
+    },
+    {
+      "epoch": 0.0665077327465004,
+      "eval_loss": 0.9951372146606445,
+      "eval_runtime": 1359.5911,
+      "eval_samples_per_second": 1.9,
+      "eval_steps_per_second": 0.633,
+      "step": 136
+    },
+    {
+      "epoch": 0.06699676019316585,
+      "grad_norm": 0.2642524540424347,
+      "learning_rate": 6.0454879312945754e-05,
+      "loss": 0.9332,
+      "step": 137
+    },
+    {
+      "epoch": 0.06748578763983129,
+      "grad_norm": 0.30863985419273376,
+      "learning_rate": 5.876436825260967e-05,
+      "loss": 1.0283,
+      "step": 138
+    },
+    {
+      "epoch": 0.06797481508649673,
+      "grad_norm": 0.5168886780738831,
+      "learning_rate": 5.708793912273911e-05,
+      "loss": 0.6723,
+      "step": 139
+    },
+    {
+      "epoch": 0.06846384253316218,
+      "grad_norm": 0.4818655848503113,
+      "learning_rate": 5.542616442234618e-05,
+      "loss": 1.1226,
+      "step": 140
     }
   ],
   "logging_steps": 1,
@@ -1003,7 +1046,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.992588163992781e+17,
+  "total_flos": 6.214535873770291e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null