Training in progress, step 77, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b19418aef8a7cd6b5e699fc18e768f4d6ade9623bd0d5ce166c2d6d37355fd
+oid sha256:f168ff95e21d7e001bd1a3b1c57099edf617adefb0c1f7ec23bbb05717a2cb7d
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f1aacb1fb33c14dfab10c45142209ca75e483b5214e07e7eb72da8bfcc0935
+oid sha256:6ef97e873fef8428d5ee45258a46de7b905c21f526cba43111d625f862ecfb7d
 size 320194002

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22deae5baca73acdf1bdd6e465712b37190f83ff08b421ce09036b19ad30759d
+oid sha256:f0c6ced4bf2df8499dc2d96058780757c73d89a1bccdc6734025259075700e12
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5792623e62c69eb6d06441cf884e7d8e99d996c1745ea35dc4e4377c5a48dc2
+oid sha256:67bd5523eb2f6525efd0012a7616311251148ea6642802ae5209bd53c6895710
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:becbc0b7a9b1e331e23f7a70974c3f85981af0327a464ead257baec11a3461c4
+oid sha256:e896da01a6c9857fb0ecb9a5c5461d55445ae811dff82321390080b9f89d0092
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a7b59d54862a0ca175393f2a7f6ae8c2a3eabcb876d78099157512c18e1fa1
+oid sha256:e44d86ae4695cd217f4cbe149c2822a38bad3d2db57b9d0bc7a48c5f181d9914
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3576cca3b6a084e5b9dbc713d787dac1e4381b121fdf3f476ee9adbb805713a7
+oid sha256:24b79c0dbdbaf1db6f5e9f86b4075e23cb507805053cd78cf5bfb81ecd493496
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9411764705882355,
+  "epoch": 3.019607843137255,
   "eval_steps": 7,
-  "global_step": 75,
+  "global_step": 77,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -620,6 +620,28 @@
       "learning_rate": 2.1970089890509527e-07,
       "loss": 0.3324,
       "step": 75
+    },
+    {
+      "epoch": 2.980392156862745,
+      "grad_norm": 0.11286412179470062,
+      "learning_rate": 5.4955425714431353e-08,
+      "loss": 0.4175,
+      "step": 76
+    },
+    {
+      "epoch": 3.019607843137255,
+      "grad_norm": 0.16945837438106537,
+      "learning_rate": 0.0,
+      "loss": 0.5248,
+      "step": 77
+    },
+    {
+      "epoch": 3.019607843137255,
+      "eval_loss": 0.41082337498664856,
+      "eval_runtime": 1.7311,
+      "eval_samples_per_second": 49.679,
+      "eval_steps_per_second": 1.733,
+      "step": 77
     }
   ],
   "logging_steps": 1,
@@ -634,12 +656,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.0956683733408154e+17,
+  "total_flos": 2.1485559026915738e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null