Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
     "q_proj",
-    "down_proj",
-    "up_proj",
     "k_proj",
-    "o_proj"
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:756ed992b06ee91192de25d1e68d7a9f6a8af259b5b02ba0eea602ce2f40f732
+oid sha256:d1ddcf6ea8f5ebbca5308a39e539f98bcc37e5b3b52ac6e3d6cb73f95e916a8e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4759dac966c836fbf4788266dd38e0108bba8e342fadf508cdf0c83343baae30
+oid sha256:63ce3360450fa2beaefeaee64c056f8b8fc3435b5b40a0dde13dac0fce2f6779
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb35249a84d7bcb3cccf7fe5b59ee8dc0f174103950c84a23cc071b3089b5686
+oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
 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

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00011351167278368459,
+  "epoch": 0.00034053501835105374,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 3.7837224261228196e-05,
-      "grad_norm": 14.805928230285645,
+      "grad_norm": 15.425179481506348,
       "learning_rate": 2e-05,
       "loss": 4.2775,
       "step": 1
@@ -18,32 +18,90 @@
     {
       "epoch": 3.7837224261228196e-05,
       "eval_loss": 1.0869630575180054,
-      "eval_runtime": 2378.1464,
-      "eval_samples_per_second": 2.34,
-      "eval_steps_per_second": 2.34,
+      "eval_runtime": 1969.7164,
+      "eval_samples_per_second": 2.825,
+      "eval_steps_per_second": 2.825,
       "step": 1
     },
     {
       "epoch": 7.567444852245639e-05,
-      "grad_norm": 14.053690910339355,
+      "grad_norm": 14.54034423828125,
       "learning_rate": 4e-05,
       "loss": 4.198,
       "step": 2
     },
     {
       "epoch": 0.00011351167278368459,
-      "grad_norm": 9.68853759765625,
+      "grad_norm": 9.865498542785645,
       "learning_rate": 6e-05,
-      "loss": 4.309,
+      "loss": 4.3061,
       "step": 3
     },
     {
       "epoch": 0.00011351167278368459,
-      "eval_loss": 0.9365310072898865,
-      "eval_runtime": 2383.4538,
-      "eval_samples_per_second": 2.334,
-      "eval_steps_per_second": 2.334,
+      "eval_loss": 0.9358382225036621,
+      "eval_runtime": 2314.6741,
+      "eval_samples_per_second": 2.404,
+      "eval_steps_per_second": 2.404,
       "step": 3
+    },
+    {
+      "epoch": 0.00015134889704491279,
+      "grad_norm": 7.155860424041748,
+      "learning_rate": 8e-05,
+      "loss": 3.874,
+      "step": 4
+    },
+    {
+      "epoch": 0.00018918612130614098,
+      "grad_norm": 4.540463924407959,
+      "learning_rate": 0.0001,
+      "loss": 3.2857,
+      "step": 5
+    },
+    {
+      "epoch": 0.00022702334556736918,
+      "grad_norm": 3.66566801071167,
+      "learning_rate": 0.00012,
+      "loss": 3.2424,
+      "step": 6
+    },
+    {
+      "epoch": 0.00022702334556736918,
+      "eval_loss": 0.7986580729484558,
+      "eval_runtime": 2384.8555,
+      "eval_samples_per_second": 2.333,
+      "eval_steps_per_second": 2.333,
+      "step": 6
+    },
+    {
+      "epoch": 0.00026486056982859735,
+      "grad_norm": 4.557755470275879,
+      "learning_rate": 0.00014,
+      "loss": 3.3631,
+      "step": 7
+    },
+    {
+      "epoch": 0.00030269779408982557,
+      "grad_norm": 3.7365407943725586,
+      "learning_rate": 0.00016,
+      "loss": 2.95,
+      "step": 8
+    },
+    {
+      "epoch": 0.00034053501835105374,
+      "grad_norm": 3.51993989944458,
+      "learning_rate": 0.00018,
+      "loss": 2.4298,
+      "step": 9
+    },
+    {
+      "epoch": 0.00034053501835105374,
+      "eval_loss": 0.6866493821144104,
+      "eval_runtime": 2377.7125,
+      "eval_samples_per_second": 2.34,
+      "eval_steps_per_second": 2.34,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -63,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2109388496044032.0,
+  "total_flos": 6328165488132096.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c49defa0185f3971ee1ec8e0038c402fa3301af18c0e87abd89a3514b3a03b4
+oid sha256:291b68746f328c8f5d6f048071017ecfa63bfb5a09e3a8555c42108a03bc05b5
 size 6776