Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144ed1d40db4028269bdc66b938d788bf81dbe8e73b32087dbf70fa1f15e5139
+oid sha256:2df5a6b832e3fdfdd82c6c562c94668162a9bd663f824219f149a72bda59ac7d
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74909fd4745e3a403b3566fddf3dfb62893b0a09e673d9c8d5cc87ed4b45acb0
+oid sha256:d179db5953f2639393b62438cf3f24f0711650c81680ec89b307284c68a94d30
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e1d4e220c2e87a35da930aab1a7ef3cfb78808e84af2a47ce768e8083ff26c
+oid sha256:11adc404f4afa2ea3172951503f9b606699637391aa83294149afb012ae79bf8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015479876160990712,
+  "epoch": 0.02321981424148607,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 4.895,
       "eval_steps_per_second": 2.452,
       "step": 20
+    },
+    {
+      "epoch": 0.016253869969040248,
+      "grad_norm": 1.8704389333724976,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.6885,
+      "step": 21
+    },
+    {
+      "epoch": 0.018575851393188854,
+      "grad_norm": 1.0107614994049072,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.4309,
+      "step": 24
+    },
+    {
+      "epoch": 0.01934984520123839,
+      "eval_loss": 1.4435930252075195,
+      "eval_runtime": 111.2717,
+      "eval_samples_per_second": 4.898,
+      "eval_steps_per_second": 2.453,
+      "step": 25
+    },
+    {
+      "epoch": 0.02089783281733746,
+      "grad_norm": 1.209702968597412,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.7998,
+      "step": 27
+    },
+    {
+      "epoch": 0.02321981424148607,
+      "grad_norm": 1.0272233486175537,
+      "learning_rate": 0.0,
+      "loss": 6.2568,
+      "step": 30
+    },
+    {
+      "epoch": 0.02321981424148607,
+      "eval_loss": 1.4408866167068481,
+      "eval_runtime": 111.248,
+      "eval_samples_per_second": 4.899,
+      "eval_steps_per_second": 2.454,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8576723457146880.0,
+  "total_flos": 1.2987609806536704e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null