Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7a83627ff01c05e4094e3a05a8d30e5f47cece4a8390a0295c65b9c730fa8f
+oid sha256:5cf440db6594c84604740fed8cda28caf0921c07c724d151bcb3cb42c39e9539
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb463840b014ca65e5b6994a26cbb8cf1e6d87287b19b54e02e2190979f5229e
+oid sha256:5bdb516b4acf1d6b65bd43cebcdad610903fb270a28a57592cef712c010bc3a8
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f119b296d80ef00a89f5792c80886b9bbb765e3d7b8cb48f0846bc9e1cae954e
+oid sha256:53cb619a5ccb222884fa3789cef341bb8e4b5441bee4ff9cd1343500f85d9d21
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:277091ad01cdb8abcbb766e00d3272fa0dd8250e65926960cf4154ec0f63d008
+oid sha256:b97d469c2d1ff6d4cb5f670c08e09df4f08fd3742fcd2f7e54012931e0d6d476
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cbe3283f5e9591df1b334dc49bb4e9afd3f9fd439b9175600fe6cc9d9a23492
+oid sha256:4ac9ecbe85481a4e8d86a388fa4c6209a870f702b0d0252aae9f9e31a5e396ad
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c780c8cbc4748c0d33bb1f396aedea1edcf7d1aef29341e247c3d420c819cd4
+oid sha256:e97c9c12b1cca18b9d68cf758cec45fb2341027dbadb09d49ba12c4f8c2ba9aa
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23595030144c30ee47c8613a1290091039a5fc1ce35281647f9e5d13b87497bb
+oid sha256:fc4f1ab2f108da9a540e579e8eb4fe7879ce1b2d4bc117501313387ab106dde1
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a8587b712892013543dc7983f3a7215192a31430f623ee6993f64fec8e28e1d
+oid sha256:fb5e132a7d035d553db132ede574b00cced69641455ad4a6157b0102cdcd0c78
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a07a2cdf7fd10b564620e5e93ca4cfdec28089ebf66627b150a0a0a39a808f
+oid sha256:912e872d3c365513889972e6f7039482d5bc50a57eb0c2d3d0c7af303ca21576
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ec34837376c33fa96eb9fac904d1666cf7054f4385e6d5e6fc121cabd431bd
+oid sha256:b3e55a4c2490cd5fee87293d304c31ce3cec1fb6ea51d17e81369ad67604328c
 size 15984

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": 0.0007841599686336013,
+  "epoch": 0.0015683199372672025,
   "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": 107.993,
       "eval_steps_per_second": 13.51,
       "step": 3
+    },
+    {
+      "epoch": 0.0010455466248448016,
+      "grad_norm": 0.7267158627510071,
+      "learning_rate": 8e-05,
+      "loss": 0.2419,
+      "step": 4
+    },
+    {
+      "epoch": 0.0013069332810560022,
+      "grad_norm": 0.5915173888206482,
+      "learning_rate": 0.0001,
+      "loss": 0.2027,
+      "step": 5
+    },
+    {
+      "epoch": 0.0015683199372672025,
+      "grad_norm": 0.4983539581298828,
+      "learning_rate": 0.00012,
+      "loss": 0.1424,
+      "step": 6
+    },
+    {
+      "epoch": 0.0015683199372672025,
+      "eval_loss": 0.17498068511486053,
+      "eval_runtime": 59.665,
+      "eval_samples_per_second": 107.986,
+      "eval_steps_per_second": 13.509,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2322534166953984.0,
+  "total_flos": 4645068333907968.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null