Training in progress, step 8, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74e4d33dac8804df1ca8a24fc70f17785330570759e30695c2b7a55a95e302d
+oid sha256:267b16c5ccdee00137664da4abae275386662939fb4daaa5e60ac9518090836d
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c7438c2c69b868b80b7cd8c90a3ed52db2ebdedc9ccf13ddf0a940bdc301f2
+oid sha256:c18f7424f1e4e6d1cb96908353fde53bda9527acd5db49971fbc85fb35606968
 size 263024

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa09197c8dbc572875a7dcb378f97f405ceb17960b8bd0159816b7dc303ffbd
+oid sha256:c17f63e4ecde32684d8daab508bc95e4fb60b42da6dcad237c0dd3151be21cc8
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2dfcaec1b8203f8d504214d1bcafbe8a3b16072868bf24337106c5d0d32261b
+oid sha256:799b858ba8010cc95a2389340a76b52c936dc0a7ec275440a87d94d2e452dd32
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5fcb77b61a3d86ba889ed3e86f4e1cd2dc044015886e25b088557f41e0eb87
+oid sha256:3f18136116fbbf8d9b045c7ff28443c53f7143d67a0ce6c8ba325061eccf527c
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4221e19d06842c1aecb8b3b5eebadd1ce1c4ac62b6ae21ad4916250383e521a3
+oid sha256:198d94423ce31e2d2b592f219e2eca5d02a987fb1a82bd5a9e9797758ceb1f92
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2483b9abdb7fbd16fa3b6920691d00273f4e2f3a0d1d37af4eb994a7f64f746
+oid sha256:e24a6b926ea4352d6ea08b02a2fd5fd4abd5648492cff00d926548288e954fe2
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee2b6f21012ef5dd700094dde658c641a7ac701837ad5f4cb74ce18f15ec04e
+oid sha256:093b1428faca2f70382056a803de21d329871ce63be030b0986cb42c8e5131d5
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9d1132dc80c4da6350b071c78feca5994d69fda87ae45cb15675cf21a0c0be
+oid sha256:a65661ebaf88a59c39ed172576b3b283adce8bd38b021ba8cb4f51a54d74663c
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3fbf2088952d3639588cfe0825db5e284e13dc9cfa6b193dbe186c1298cd049
+oid sha256:3998529b7cdd0eabe7e1c8d3a03005ab0e866780f30f07533f233bc623c1f71c
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2782608695652174,
+  "epoch": 0.5565217391304348,
   "eval_steps": 4,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,42 @@
       "eval_samples_per_second": 896.219,
       "eval_steps_per_second": 120.112,
       "step": 4
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 7.8040056228637695,
+      "learning_rate": 5e-05,
+      "loss": 177.4141,
+      "step": 5
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 8.207115173339844,
+      "learning_rate": 6e-05,
+      "loss": 177.3047,
+      "step": 6
+    },
+    {
+      "epoch": 0.48695652173913045,
+      "grad_norm": 7.859698295593262,
+      "learning_rate": 7e-05,
+      "loss": 177.2422,
+      "step": 7
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "grad_norm": 7.5123820304870605,
+      "learning_rate": 8e-05,
+      "loss": 177.1875,
+      "step": 8
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "eval_loss": 11.06894302368164,
+      "eval_runtime": 0.1066,
+      "eval_samples_per_second": 909.671,
+      "eval_steps_per_second": 121.915,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5324685705216.0,
+  "total_flos": 10649371410432.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null