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:e5a5e005137712b7b1e7d01a499bf57cc12fd7ee85152fd28754b8c4da478663
+oid sha256:365aa4a8be46fa54fa865bcafa6a4dfe007d56652a0d5c06ca7d0636a0f5a209
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a94922e5a44a7c3c84d84db479b4a7d769ed259e2f6a55b266d59991118b58
+oid sha256:086362e2ba798149ff26a460ab6c64f40090f56448b19e4edf10b49ae53c3f34
 size 37965300

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f493e274c1837716c70dd4cfbea04067e7d4ea42e522469e14da4197034ac09f
+oid sha256:74eff1aaeb23f7c5da967314ef09fcadcf8dd98129b2e23c18e30cad1f3d98d1
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1823c47738035cc4399c12a8fe7e2516958c0c3f40beeb253a31ae33c12af2e
+oid sha256:9851603423fb43d1355a5f5983f8e9d76c57606e6f614a7bfe4a891b37432eea
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022cd96e0f2d9875b8c59152008a68e54288e66b8e9fea7b892c318c6c66ecb8
+oid sha256:4f46fb008ba3c7da3e9e101bf4ecbc4bad6629c45b9309b3e086e9f7d532acc7
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a12d86f432a992673250080fe8bb69a6e8afe0e7250966db125d312c71feb19
+oid sha256:fe7a6ab6b0ef57f3a70c2600dd377e8e8143fc9aff53ed8b18bdb97f0a7530a4
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e729565b8fcaedf949cc2d3fe412be11a510eb5239d4a8c5d856af267ee93fa
+oid sha256:ad8d67cb450b52f0e8c119bc12056288e233502618cc60a00093b7235d32690f
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e197b9a46ebb9502125209d956656c70d2d780bdc6a59aabf069f8354f82889b
+oid sha256:3557a500edd97558f50d759c9608b3728faa270af5958bea28917da46b71cc49
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89d1ab2d1f13d7eb0106630bd5c703050860788d67169147d75a7b1c3317bf6
+oid sha256:89293bd36a457766675f173525438c12fe41efee6816a576f7c754bf87d895da
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858a26dbc9defa25aace37aff959e7ece37eaf919502a45dfde9413694a4a6cf
+oid sha256:a39ad3dac0593de5b65cfc5b98fe9ccb8faf46a1295e7f40744e13cdcda701a9
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008781558726673985,
+  "epoch": 0.001756311745334797,
   "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": 80.013,
       "eval_steps_per_second": 10.012,
       "step": 3
+    },
+    {
+      "epoch": 0.0011708744968898647,
+      "grad_norm": 3.715500593185425,
+      "learning_rate": 6e-05,
+      "loss": 9.3834,
+      "step": 4
+    },
+    {
+      "epoch": 0.0014635931211123307,
+      "grad_norm": 4.088770866394043,
+      "learning_rate": 8e-05,
+      "loss": 9.2807,
+      "step": 5
+    },
+    {
+      "epoch": 0.001756311745334797,
+      "grad_norm": 3.8607888221740723,
+      "learning_rate": 0.0001,
+      "loss": 8.6573,
+      "step": 6
+    },
+    {
+      "epoch": 0.001756311745334797,
+      "eval_loss": 8.29586124420166,
+      "eval_runtime": 71.9482,
+      "eval_samples_per_second": 79.974,
+      "eval_steps_per_second": 10.007,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3135045208375296.0,
+  "total_flos": 6270090416750592.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null