Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618d4dffa48aa304c89e57556f5a754f77703341912518007c0973875435650d
+oid sha256:3e782ae28c83ad95c50cb7b75c44ef384af5a69f0cae662f258d1d3dcdf7ff30
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7263f6678616c895fcb41276c3a31a171dd3cc7d8b9b556e243780ec5aee8f
+oid sha256:03ee81f13e084caf1a540c1e606ccff8b13d91d5fe4e5a7bfc4ce88a4dccbb88
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e378f86598b07f914582636a0353a13b8e8c042e0abc3b7613d98f9ca9baf0b
+oid sha256:f55c5b61e12de66e3bcc648880843598fd156763bed4c21407f6cd457f38adcc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.25,
+  "epoch": 4.5,
   "eval_steps": 1,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,81 @@
       "eval_samples_per_second": 31.025,
       "eval_steps_per_second": 3.103,
       "step": 5
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.2225133180618286,
+      "learning_rate": 0.00012,
+      "loss": 1.2449,
+      "step": 6
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 1.2144503593444824,
+      "eval_runtime": 3.7582,
+      "eval_samples_per_second": 26.608,
+      "eval_steps_per_second": 2.661,
+      "step": 6
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 0.3669193685054779,
+      "learning_rate": 0.00014,
+      "loss": 1.2385,
+      "step": 7
+    },
+    {
+      "epoch": 3.125,
+      "eval_loss": 1.2128633260726929,
+      "eval_runtime": 3.2002,
+      "eval_samples_per_second": 31.248,
+      "eval_steps_per_second": 3.125,
+      "step": 7
+    },
+    {
+      "epoch": 3.625,
+      "grad_norm": 0.44991809129714966,
+      "learning_rate": 0.00016,
+      "loss": 1.2142,
+      "step": 8
+    },
+    {
+      "epoch": 3.625,
+      "eval_loss": 1.2061299085617065,
+      "eval_runtime": 3.2088,
+      "eval_samples_per_second": 31.164,
+      "eval_steps_per_second": 3.116,
+      "step": 8
+    },
+    {
+      "epoch": 4.125,
+      "grad_norm": 0.3696751296520233,
+      "learning_rate": 0.00018,
+      "loss": 1.2725,
+      "step": 9
+    },
+    {
+      "epoch": 4.125,
+      "eval_loss": 1.1926738023757935,
+      "eval_runtime": 3.7129,
+      "eval_samples_per_second": 26.933,
+      "eval_steps_per_second": 2.693,
+      "step": 9
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.227733314037323,
+      "learning_rate": 0.0002,
+      "loss": 1.2282,
+      "step": 10
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 1.1847997903823853,
+      "eval_runtime": 3.6889,
+      "eval_samples_per_second": 27.108,
+      "eval_steps_per_second": 2.711,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -96,12 +171,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4510872430706688.0,
+  "total_flos": 9020988828155904.0,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null