Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe9cfacff2ee2c838f875570b6b0958916525f27546e1bf66442f6239b4e1bc
+oid sha256:f8e55c3be663cea5f316f75b26d0b9f2b186eb2a3a48a5830b922e95b7bc1176
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20d16ac7aae12c14f27f6023ae06a39ff9ee8e53c00177830ff83692572e2566
+oid sha256:d58357a799aa2bc8139fdedce4aa015f85c4e38ba39a5605316c3fa05595aee3
 size 111142

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47bae1b5c9282ac7de84cc33b69b1ec121f93abe3c756b9084beaa1f2f69b786
+oid sha256:59b1d024865d1dba4562580f93959a5a2b1a3bf90213c135f90f60d80b11a78f
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185f5d8bae35531eb92aff5e246f90aae9cbc4611edc71c21b181fedac723eb7
+oid sha256:deb5f3237ae88e14981a5756b110880ad688694abd0ba11e55e250f561e35622
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ed002b6793d191eb5d81853f467547398138101cf4e16200650672365c189d
+oid sha256:003ef98a2b528861f4d1487387f772d8aae3ed53d6011e15552c6470cc539ea0
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0a782e233cbfaf703333e443353e5f6ab546e8f11ff4658674f4878030f9122
+oid sha256:ef69ffd171970264b348a13a56d94173b99be6aba5621fe1853099ef1072f676
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c195a5153313a2949ee729ac4591d5ddae84417780c3d35ca80a52f6a04cd51a
+oid sha256:ceaad68722e6ed00d9beef3e50e10f519480af690b63e499fc9f8f89515238f0
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0d6d6c0a9d51a7ba3d8c265044569c1d30d022950b58bf33f790680076be7bf
+oid sha256:fa0bb24fa34cfe9d00b78207938758f5303233d6bbff724241e845b94631cc63
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3166300144cd43c32119aac322f801c9f02afad107c4ef2772ee7d924536f1f
+oid sha256:454e536cf797be7dff220575f47b93c8cc77ccc1c55d5df7d2ad74af6d2539ec
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4b42862bba6e0c0adead6fa007917ef588b7069f7bcc2a60375a4cad60e48b
+oid sha256:e2a659e458bf3cb1ed92f049ddb671d64664d3fce5039b5ec93eee2595122a80
 size 15984

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": 0.05873715124816446,
+  "epoch": 0.0881057268722467,
   "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": 798.388,
       "eval_steps_per_second": 100.234,
       "step": 10
+    },
+    {
+      "epoch": 0.06461086637298091,
+      "grad_norm": 0.08185140043497086,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 10.3807,
+      "step": 11
+    },
+    {
+      "epoch": 0.07048458149779736,
+      "grad_norm": 0.07860841602087021,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3804,
+      "step": 12
+    },
+    {
+      "epoch": 0.0763582966226138,
+      "grad_norm": 0.08291763812303543,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3801,
+      "step": 13
+    },
+    {
+      "epoch": 0.08223201174743025,
+      "grad_norm": 0.07697901129722595,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.3793,
+      "step": 14
+    },
+    {
+      "epoch": 0.0881057268722467,
+      "grad_norm": 0.08883082866668701,
+      "learning_rate": 5e-05,
+      "loss": 10.3791,
+      "step": 15
+    },
+    {
+      "epoch": 0.0881057268722467,
+      "eval_loss": NaN,
+      "eval_runtime": 1.4409,
+      "eval_samples_per_second": 796.022,
+      "eval_steps_per_second": 99.936,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 16736782909440.0,
+  "total_flos": 25105174364160.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null