Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c5944bfbabb758c861575ab888ea83bc13e4f486102d11c64d47e82145e80b
+oid sha256:c6d522349ee4ae9671414ae9c9149fe09a55597dff6b042f40220e646137de2b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1993c70f0c8618cb7c9ee059b51c647b224d05f600295232dbd98d1040ab3a5
+oid sha256:ee5bc8844c912b289da9b9cf78d692244df88d93fd47c32cba28fbf1a677fb2f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017777777777777778,
+  "epoch": 0.035555555555555556,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 32.279,
       "eval_steps_per_second": 16.367,
       "step": 3
+    },
+    {
+      "epoch": 0.023703703703703703,
+      "grad_norm": 10.761432647705078,
+      "learning_rate": 8e-05,
+      "loss": 14.8401,
+      "step": 4
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 11.122270584106445,
+      "learning_rate": 0.0001,
+      "loss": 14.4769,
+      "step": 5
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 16.866044998168945,
+      "learning_rate": 0.00012,
+      "loss": 13.9125,
+      "step": 6
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "eval_loss": 13.018987655639648,
+      "eval_runtime": 2.2115,
+      "eval_samples_per_second": 32.105,
+      "eval_steps_per_second": 16.278,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1109738548887552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null