Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a003ed1fb53b81bc7b622de55c1c33b245bbf634fa78f9a1616406c5413ab64
+oid sha256:ef3f786a86e552230a6744418d89b2e9b72ab9188269095875170275a85d1723
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0479e9d7a6f70a0bf77141e72134c8b35477028b4e36900e0fc842b81e70c94
+oid sha256:a0aa7fa4d55ad1c4ad59d4e241f93cca7b97b7ec03c9e095c6a83317514b8d00
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6133c2d18dfd4106160fc1357511962bfa6f38646ba33c534203e63fb2eae6
+oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001415261233636042,
+  "epoch": 0.004245783700908126,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,64 @@
       "eval_samples_per_second": 64.546,
       "eval_steps_per_second": 32.309,
       "step": 3
+    },
+    {
+      "epoch": 0.0018870149781813894,
+      "grad_norm": 0.026352746412158012,
+      "learning_rate": 8e-05,
+      "loss": 10.3762,
+      "step": 4
+    },
+    {
+      "epoch": 0.0023587687227267368,
+      "grad_norm": 0.03207406401634216,
+      "learning_rate": 0.0001,
+      "loss": 10.3863,
+      "step": 5
+    },
+    {
+      "epoch": 0.002830522467272084,
+      "grad_norm": 0.027389129623770714,
+      "learning_rate": 0.00012,
+      "loss": 10.3768,
+      "step": 6
+    },
+    {
+      "epoch": 0.002830522467272084,
+      "eval_loss": 10.383142471313477,
+      "eval_runtime": 17.7035,
+      "eval_samples_per_second": 50.442,
+      "eval_steps_per_second": 25.249,
+      "step": 6
+    },
+    {
+      "epoch": 0.0033022762118174315,
+      "grad_norm": 0.021352829411625862,
+      "learning_rate": 0.00014,
+      "loss": 10.3891,
+      "step": 7
+    },
+    {
+      "epoch": 0.003774029956362779,
+      "grad_norm": 0.027664244174957275,
+      "learning_rate": 0.00016,
+      "loss": 10.3855,
+      "step": 8
+    },
+    {
+      "epoch": 0.004245783700908126,
+      "grad_norm": 0.022455623373389244,
+      "learning_rate": 0.00018,
+      "loss": 10.3806,
+      "step": 9
+    },
+    {
+      "epoch": 0.004245783700908126,
+      "eval_loss": 10.38300895690918,
+      "eval_runtime": 15.2241,
+      "eval_samples_per_second": 58.657,
+      "eval_steps_per_second": 29.361,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -55,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 77585448960.0,
+  "total_flos": 232756346880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null