Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f2132f32ccbd67404a712d88a7e812144c0f3edb27f1e1cb20412336934eca6
+oid sha256:02fd5271a5082d3dd10553ac0dacaa52dba51457a3aff74307473b63cefe6c4a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2104b605345c12583b245679556fd51c5934ff960d02849030cd7cf015b6e6f0
+oid sha256:66aa0e4c989e12a95f6f42d22c36bda35597bfe1e03ceefb281b2327e1df82cf
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eedb2a7e70cd3ddb5e4b069afa99ed1d476536fe99262e3af8da16dc7f01adbf
+oid sha256:3465f7c25c9aa7b7d0f0ef97318a58a46caf1594972ff0b6ab587309c9932dd4
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e1693efd3253b65c059352e1453da814f21eb02ddf59e0d5b362c9c1691055
+oid sha256:9246be5539fbdfee7619655397cf993f2cfdd3b876b2e2fabfeeeb5329222011
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2476780185758514,
+  "epoch": 0.3715170278637771,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 10.966,
       "eval_steps_per_second": 2.741,
       "step": 10
+    },
+    {
+      "epoch": 0.2724458204334365,
+      "grad_norm": 1.872157335281372,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.3498,
+      "step": 11
+    },
+    {
+      "epoch": 0.29721362229102166,
+      "grad_norm": 1.768731713294983,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.0483,
+      "step": 12
+    },
+    {
+      "epoch": 0.3219814241486068,
+      "grad_norm": 2.154233455657959,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.0541,
+      "step": 13
+    },
+    {
+      "epoch": 0.34674922600619196,
+      "grad_norm": 2.210120677947998,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1021,
+      "step": 14
+    },
+    {
+      "epoch": 0.3715170278637771,
+      "grad_norm": 1.6423015594482422,
+      "learning_rate": 5e-05,
+      "loss": 2.1531,
+      "step": 15
+    },
+    {
+      "epoch": 0.3715170278637771,
+      "eval_loss": 2.1677563190460205,
+      "eval_runtime": 24.832,
+      "eval_samples_per_second": 10.954,
+      "eval_steps_per_second": 2.738,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3740393073934336e+17,
+  "total_flos": 3.5610589610901504e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null