Training in progress, step 135, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03564a29944f743d7ff67c8a1dfaf6dd893a50fa893b5c13b3393b17aa1c576b
+oid sha256:0a5829c1aaac0370fbc9f55a10a44686e06dcf6a61472d1007b0ca63686efff4
 size 278979768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ae2ce54e8d42d573fff28851279fdce2d44c7dc58f7376e00dae7956178023
+oid sha256:aacfad5be4ee84d37602fc40976c81cf13e482d10905721669d5f26b8307caa3
 size 558179131

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d958415f40e967020c50c5463e8b5f28a31975f8553a3b0737c1fe5f11e59d
+oid sha256:9d869e0cd2d34a9404d767c73261715c7815100078a678b556e5244942642e69
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a01efb27201589921dd7914fb6c1f6857fe6f9bcf9cf1d909134ca0d4c75d9
+oid sha256:f0d5bd5a0c1552b248a35fd6047976779f0285efac8e4a1d87b2e9f236df2b3b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2222222222222223,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 135,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,55 @@
       "learning_rate": 5.333333333333333e-05,
       "loss": 0.4918,
       "step": 100
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.20853544771671295,
+      "learning_rate": 4.592592592592593e-05,
+      "loss": 0.369,
+      "step": 105
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.15505483746528625,
+      "learning_rate": 3.851851851851852e-05,
+      "loss": 0.4781,
+      "step": 110
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 0.23773588240146637,
+      "learning_rate": 3.111111111111111e-05,
+      "loss": 0.4814,
+      "step": 115
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.1105145588517189,
+      "learning_rate": 2.3703703703703707e-05,
+      "loss": 0.3814,
+      "step": 120
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.2347269505262375,
+      "learning_rate": 1.62962962962963e-05,
+      "loss": 0.3766,
+      "step": 125
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.21751029789447784,
+      "learning_rate": 8.88888888888889e-06,
+      "loss": 0.3975,
+      "step": 130
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.24321921169757843,
+      "learning_rate": 1.4814814814814817e-06,
+      "loss": 0.5574,
+      "step": 135
     }
   ],
   "logging_steps": 5,
@@ -162,12 +211,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2112790202925056e+16,
+  "total_flos": 1.6395167402459136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null